single_stock_n-step_sarsa.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import random\n",
    "\n",
    "from finrl.meta.env_portfolio_allocation import env_portfolio\n",
    "import pandas as pd\n",
    "import numpy as np\n",
    "import gym\n",
    "from typing import Callable, Tuple\n",
    "from collections import defaultdict\n",
    "from tqdm import trange"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Users/scott/opt/anaconda3/envs/FinRL/lib/python3.10/site-packages/pyfolio/pos.py:26: UserWarning: Module \"zipline.assets\" not found; mutltipliers will not be applied to position notionals.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['AXP', 'AMGN', 'AAPL', 'BA', 'CAT', 'CSCO', 'CVX', 'GS', 'HD', 'HON', 'IBM', 'INTC', 'JNJ', 'KO', 'JPM', 'MCD', 'MMM', 'MRK', 'MSFT', 'NKE', 'PG', 'TRV', 'UNH', 'CRM', 'VZ', 'V', 'WBA', 'WMT', 'DIS', 'DOW']\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "[*********************100%%**********************]  1 of 1 completed\n",
      "Shape of DataFrame:  (101615, 8)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "(101615, 8)"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "############STUFF GRABBED FROM FINRL TUTORIAL\n",
    "import matplotlib\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "matplotlib.use('Agg')\n",
    "%matplotlib inline\n",
    "import datetime\n",
    "\n",
    "from finrl import config\n",
    "from finrl import config_tickers\n",
    "from finrl.meta.preprocessor.yahoodownloader import YahooDownloader\n",
    "from finrl.meta.preprocessor.preprocessors import FeatureEngineer, data_split\n",
    "from finrl.meta.env_portfolio_allocation.env_portfolio import StockPortfolioEnv\n",
    "from finrl.agents.stablebaselines3.models import DRLAgent\n",
    "from finrl.plot import backtest_stats, backtest_plot, get_daily_return, get_baseline, convert_daily_return_to_pyfolio_ts\n",
    "from finrl.meta.data_processor import DataProcessor\n",
    "from finrl.meta.data_processors.processor_yahoofinance import YahooFinanceProcessor\n",
    "import sys\n",
    "\n",
    "## 2.4. Create Folders\n",
    "import os\n",
    "\n",
    "if not os.path.exists(\"./\" + config.DATA_SAVE_DIR):\n",
    "    os.makedirs(\"./\" + config.DATA_SAVE_DIR)\n",
    "if not os.path.exists(\"./\" + config.TRAINED_MODEL_DIR):\n",
    "    os.makedirs(\"./\" + config.TRAINED_MODEL_DIR)\n",
    "if not os.path.exists(\"./\" + config.TENSORBOARD_LOG_DIR):\n",
    "    os.makedirs(\"./\" + config.TENSORBOARD_LOG_DIR)\n",
    "if not os.path.exists(\"./\" + config.RESULTS_DIR):\n",
    "    os.makedirs(\"./\" + config.RESULTS_DIR)\n",
    "\n",
    "print(config_tickers.DOW_30_TICKER)\n",
    "#dp = YahooFinanceProcessor()\n",
    "#df = dp.download_data\n",
    "\n",
    "df = YahooDownloader(start_date='2008-01-01',\n",
    "                     end_date='2021-10-31',\n",
    "                     ticker_list=config_tickers.DOW_30_TICKER).fetch_data()\n",
    "\n",
    "df.head()\n",
    "df.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Successfully added technical indicators\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>open</th>\n",
       "      <th>high</th>\n",
       "      <th>low</th>\n",
       "      <th>close</th>\n",
       "      <th>volume</th>\n",
       "      <th>tic</th>\n",
       "      <th>day</th>\n",
       "      <th>macd</th>\n",
       "      <th>boll_ub</th>\n",
       "      <th>boll_lb</th>\n",
       "      <th>rsi_30</th>\n",
       "      <th>cci_30</th>\n",
       "      <th>dx_30</th>\n",
       "      <th>close_30_sma</th>\n",
       "      <th>close_60_sma</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2008-01-02</td>\n",
       "      <td>7.116786</td>\n",
       "      <td>7.152143</td>\n",
       "      <td>6.876786</td>\n",
       "      <td>5.898639</td>\n",
       "      <td>1079178800</td>\n",
       "      <td>AAPL</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.903858</td>\n",
       "      <td>5.896147</td>\n",
       "      <td>100.0</td>\n",
       "      <td>-66.666667</td>\n",
       "      <td>100.0</td>\n",
       "      <td>5.898639</td>\n",
       "      <td>5.898639</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3483</th>\n",
       "      <td>2008-01-02</td>\n",
       "      <td>46.599998</td>\n",
       "      <td>47.040001</td>\n",
       "      <td>46.259998</td>\n",
       "      <td>33.761421</td>\n",
       "      <td>7934400</td>\n",
       "      <td>AMGN</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.903858</td>\n",
       "      <td>5.896147</td>\n",
       "      <td>100.0</td>\n",
       "      <td>-66.666667</td>\n",
       "      <td>100.0</td>\n",
       "      <td>33.761421</td>\n",
       "      <td>33.761421</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6966</th>\n",
       "      <td>2008-01-02</td>\n",
       "      <td>52.090000</td>\n",
       "      <td>52.320000</td>\n",
       "      <td>50.790001</td>\n",
       "      <td>39.588001</td>\n",
       "      <td>8053700</td>\n",
       "      <td>AXP</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.903858</td>\n",
       "      <td>5.896147</td>\n",
       "      <td>100.0</td>\n",
       "      <td>-66.666667</td>\n",
       "      <td>100.0</td>\n",
       "      <td>39.588001</td>\n",
       "      <td>39.588001</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10449</th>\n",
       "      <td>2008-01-02</td>\n",
       "      <td>87.570000</td>\n",
       "      <td>87.839996</td>\n",
       "      <td>86.000000</td>\n",
       "      <td>63.481617</td>\n",
       "      <td>4303000</td>\n",
       "      <td>BA</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.903858</td>\n",
       "      <td>5.896147</td>\n",
       "      <td>100.0</td>\n",
       "      <td>-66.666667</td>\n",
       "      <td>100.0</td>\n",
       "      <td>63.481617</td>\n",
       "      <td>63.481617</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13932</th>\n",
       "      <td>2008-01-02</td>\n",
       "      <td>72.559998</td>\n",
       "      <td>72.669998</td>\n",
       "      <td>70.050003</td>\n",
       "      <td>45.605484</td>\n",
       "      <td>6337800</td>\n",
       "      <td>CAT</td>\n",
       "      <td>2</td>\n",
       "      <td>0.0</td>\n",
       "      <td>5.903858</td>\n",
       "      <td>5.896147</td>\n",
       "      <td>100.0</td>\n",
       "      <td>-66.666667</td>\n",
       "      <td>100.0</td>\n",
       "      <td>45.605484</td>\n",
       "      <td>45.605484</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             date       open       high        low      close      volume  \\\n",
       "0      2008-01-02   7.116786   7.152143   6.876786   5.898639  1079178800   \n",
       "3483   2008-01-02  46.599998  47.040001  46.259998  33.761421     7934400   \n",
       "6966   2008-01-02  52.090000  52.320000  50.790001  39.588001     8053700   \n",
       "10449  2008-01-02  87.570000  87.839996  86.000000  63.481617     4303000   \n",
       "13932  2008-01-02  72.559998  72.669998  70.050003  45.605484     6337800   \n",
       "\n",
       "        tic  day  macd   boll_ub   boll_lb  rsi_30     cci_30  dx_30  \\\n",
       "0      AAPL    2   0.0  5.903858  5.896147   100.0 -66.666667  100.0   \n",
       "3483   AMGN    2   0.0  5.903858  5.896147   100.0 -66.666667  100.0   \n",
       "6966    AXP    2   0.0  5.903858  5.896147   100.0 -66.666667  100.0   \n",
       "10449    BA    2   0.0  5.903858  5.896147   100.0 -66.666667  100.0   \n",
       "13932   CAT    2   0.0  5.903858  5.896147   100.0 -66.666667  100.0   \n",
       "\n",
       "       close_30_sma  close_60_sma  \n",
       "0          5.898639      5.898639  \n",
       "3483      33.761421     33.761421  \n",
       "6966      39.588001     39.588001  \n",
       "10449     63.481617     63.481617  \n",
       "13932     45.605484     45.605484  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "fe = FeatureEngineer(\n",
    "    use_technical_indicator=True,\n",
    "    use_turbulence=False,\n",
    "    user_defined_feature=False)\n",
    "\n",
    "df = fe.preprocess_data(df)\n",
    "df.shape\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>open</th>\n",
       "      <th>high</th>\n",
       "      <th>low</th>\n",
       "      <th>close</th>\n",
       "      <th>volume</th>\n",
       "      <th>tic</th>\n",
       "      <th>day</th>\n",
       "      <th>macd</th>\n",
       "      <th>boll_ub</th>\n",
       "      <th>boll_lb</th>\n",
       "      <th>rsi_30</th>\n",
       "      <th>cci_30</th>\n",
       "      <th>dx_30</th>\n",
       "      <th>close_30_sma</th>\n",
       "      <th>close_60_sma</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>83591</th>\n",
       "      <td>2021-10-29</td>\n",
       "      <td>162.130005</td>\n",
       "      <td>162.440002</td>\n",
       "      <td>160.660004</td>\n",
       "      <td>153.936401</td>\n",
       "      <td>1314100</td>\n",
       "      <td>TRV</td>\n",
       "      <td>4</td>\n",
       "      <td>1.424914</td>\n",
       "      <td>156.635665</td>\n",
       "      <td>144.752577</td>\n",
       "      <td>55.691982</td>\n",
       "      <td>130.838278</td>\n",
       "      <td>19.622993</td>\n",
       "      <td>149.630913</td>\n",
       "      <td>150.155368</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>87074</th>\n",
       "      <td>2021-10-29</td>\n",
       "      <td>454.410004</td>\n",
       "      <td>461.390015</td>\n",
       "      <td>453.059998</td>\n",
       "      <td>446.448090</td>\n",
       "      <td>2497800</td>\n",
       "      <td>UNH</td>\n",
       "      <td>4</td>\n",
       "      <td>12.768889</td>\n",
       "      <td>458.350879</td>\n",
       "      <td>365.485245</td>\n",
       "      <td>67.009719</td>\n",
       "      <td>145.342648</td>\n",
       "      <td>52.064871</td>\n",
       "      <td>405.058988</td>\n",
       "      <td>404.183500</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>90557</th>\n",
       "      <td>2021-10-29</td>\n",
       "      <td>52.500000</td>\n",
       "      <td>53.049999</td>\n",
       "      <td>52.410000</td>\n",
       "      <td>46.802307</td>\n",
       "      <td>17763200</td>\n",
       "      <td>VZ</td>\n",
       "      <td>4</td>\n",
       "      <td>-0.170569</td>\n",
       "      <td>48.086329</td>\n",
       "      <td>45.189775</td>\n",
       "      <td>46.685009</td>\n",
       "      <td>-39.966408</td>\n",
       "      <td>12.569826</td>\n",
       "      <td>46.875142</td>\n",
       "      <td>47.474614</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>94040</th>\n",
       "      <td>2021-10-29</td>\n",
       "      <td>46.860001</td>\n",
       "      <td>47.279999</td>\n",
       "      <td>46.770000</td>\n",
       "      <td>41.523605</td>\n",
       "      <td>4999000</td>\n",
       "      <td>WBA</td>\n",
       "      <td>4</td>\n",
       "      <td>-0.169815</td>\n",
       "      <td>44.202654</td>\n",
       "      <td>40.524219</td>\n",
       "      <td>45.913462</td>\n",
       "      <td>-97.394877</td>\n",
       "      <td>0.268701</td>\n",
       "      <td>42.391107</td>\n",
       "      <td>42.889372</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>97523</th>\n",
       "      <td>2021-10-29</td>\n",
       "      <td>147.910004</td>\n",
       "      <td>150.100006</td>\n",
       "      <td>147.559998</td>\n",
       "      <td>144.852417</td>\n",
       "      <td>7340900</td>\n",
       "      <td>WMT</td>\n",
       "      <td>4</td>\n",
       "      <td>1.795641</td>\n",
       "      <td>147.887258</td>\n",
       "      <td>129.205260</td>\n",
       "      <td>59.710649</td>\n",
       "      <td>130.750293</td>\n",
       "      <td>35.423702</td>\n",
       "      <td>138.057023</td>\n",
       "      <td>140.642313</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             date        open        high         low       close    volume  \\\n",
       "83591  2021-10-29  162.130005  162.440002  160.660004  153.936401   1314100   \n",
       "87074  2021-10-29  454.410004  461.390015  453.059998  446.448090   2497800   \n",
       "90557  2021-10-29   52.500000   53.049999   52.410000   46.802307  17763200   \n",
       "94040  2021-10-29   46.860001   47.279999   46.770000   41.523605   4999000   \n",
       "97523  2021-10-29  147.910004  150.100006  147.559998  144.852417   7340900   \n",
       "\n",
       "       tic  day       macd     boll_ub     boll_lb     rsi_30      cci_30  \\\n",
       "83591  TRV    4   1.424914  156.635665  144.752577  55.691982  130.838278   \n",
       "87074  UNH    4  12.768889  458.350879  365.485245  67.009719  145.342648   \n",
       "90557   VZ    4  -0.170569   48.086329   45.189775  46.685009  -39.966408   \n",
       "94040  WBA    4  -0.169815   44.202654   40.524219  45.913462  -97.394877   \n",
       "97523  WMT    4   1.795641  147.887258  129.205260  59.710649  130.750293   \n",
       "\n",
       "           dx_30  close_30_sma  close_60_sma  \n",
       "83591  19.622993    149.630913    150.155368  \n",
       "87074  52.064871    405.058988    404.183500  \n",
       "90557  12.569826     46.875142     47.474614  \n",
       "94040   0.268701     42.391107     42.889372  \n",
       "97523  35.423702    138.057023    140.642313  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.tail()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>open</th>\n",
       "      <th>high</th>\n",
       "      <th>low</th>\n",
       "      <th>close</th>\n",
       "      <th>volume</th>\n",
       "      <th>tic</th>\n",
       "      <th>day</th>\n",
       "      <th>macd</th>\n",
       "      <th>boll_ub</th>\n",
       "      <th>boll_lb</th>\n",
       "      <th>rsi_30</th>\n",
       "      <th>cci_30</th>\n",
       "      <th>dx_30</th>\n",
       "      <th>close_30_sma</th>\n",
       "      <th>close_60_sma</th>\n",
       "      <th>cov_list</th>\n",
       "      <th>return_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2008-12-31</td>\n",
       "      <td>3.070357</td>\n",
       "      <td>3.133571</td>\n",
       "      <td>3.047857</td>\n",
       "      <td>2.583910</td>\n",
       "      <td>607541200</td>\n",
       "      <td>AAPL</td>\n",
       "      <td>2</td>\n",
       "      <td>-0.082603</td>\n",
       "      <td>3.093652</td>\n",
       "      <td>2.454291</td>\n",
       "      <td>42.254789</td>\n",
       "      <td>-80.462511</td>\n",
       "      <td>16.129793</td>\n",
       "      <td>2.749560</td>\n",
       "      <td>2.861671</td>\n",
       "      <td>[[0.0013489692418775557, 0.0004284139989242508...</td>\n",
       "      <td>tic             AAPL      AMGN       AXP      ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2008-12-31</td>\n",
       "      <td>57.110001</td>\n",
       "      <td>58.220001</td>\n",
       "      <td>57.060001</td>\n",
       "      <td>41.839535</td>\n",
       "      <td>6287200</td>\n",
       "      <td>AMGN</td>\n",
       "      <td>2</td>\n",
       "      <td>0.156758</td>\n",
       "      <td>42.707023</td>\n",
       "      <td>40.853199</td>\n",
       "      <td>51.060642</td>\n",
       "      <td>51.523672</td>\n",
       "      <td>10.432018</td>\n",
       "      <td>41.058033</td>\n",
       "      <td>40.603775</td>\n",
       "      <td>[[0.0013489692418775557, 0.0004284139989242508...</td>\n",
       "      <td>tic             AAPL      AMGN       AXP      ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2008-12-31</td>\n",
       "      <td>17.969999</td>\n",
       "      <td>18.750000</td>\n",
       "      <td>17.910000</td>\n",
       "      <td>14.580750</td>\n",
       "      <td>9625600</td>\n",
       "      <td>AXP</td>\n",
       "      <td>2</td>\n",
       "      <td>-0.935583</td>\n",
       "      <td>18.646867</td>\n",
       "      <td>12.660477</td>\n",
       "      <td>42.554828</td>\n",
       "      <td>-75.437694</td>\n",
       "      <td>25.776759</td>\n",
       "      <td>15.744065</td>\n",
       "      <td>17.616374</td>\n",
       "      <td>[[0.0013489692418775557, 0.0004284139989242508...</td>\n",
       "      <td>tic             AAPL      AMGN       AXP      ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>2008-12-31</td>\n",
       "      <td>41.590000</td>\n",
       "      <td>43.049999</td>\n",
       "      <td>41.500000</td>\n",
       "      <td>32.005890</td>\n",
       "      <td>5443100</td>\n",
       "      <td>BA</td>\n",
       "      <td>2</td>\n",
       "      <td>-0.279801</td>\n",
       "      <td>32.174381</td>\n",
       "      <td>28.867833</td>\n",
       "      <td>47.440243</td>\n",
       "      <td>156.994917</td>\n",
       "      <td>5.366299</td>\n",
       "      <td>30.327211</td>\n",
       "      <td>32.389914</td>\n",
       "      <td>[[0.0013489692418775557, 0.0004284139989242508...</td>\n",
       "      <td>tic             AAPL      AMGN       AXP      ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>2008-12-31</td>\n",
       "      <td>43.700001</td>\n",
       "      <td>45.099998</td>\n",
       "      <td>43.700001</td>\n",
       "      <td>29.608652</td>\n",
       "      <td>6277400</td>\n",
       "      <td>CAT</td>\n",
       "      <td>2</td>\n",
       "      <td>0.655611</td>\n",
       "      <td>30.348091</td>\n",
       "      <td>25.455647</td>\n",
       "      <td>51.205303</td>\n",
       "      <td>98.374108</td>\n",
       "      <td>26.331746</td>\n",
       "      <td>26.689551</td>\n",
       "      <td>26.423592</td>\n",
       "      <td>[[0.0013489692418775557, 0.0004284139989242508...</td>\n",
       "      <td>tic             AAPL      AMGN       AXP      ...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         date       open       high        low      close     volume   tic  \\\n",
       "0  2008-12-31   3.070357   3.133571   3.047857   2.583910  607541200  AAPL   \n",
       "1  2008-12-31  57.110001  58.220001  57.060001  41.839535    6287200  AMGN   \n",
       "2  2008-12-31  17.969999  18.750000  17.910000  14.580750    9625600   AXP   \n",
       "3  2008-12-31  41.590000  43.049999  41.500000  32.005890    5443100    BA   \n",
       "4  2008-12-31  43.700001  45.099998  43.700001  29.608652    6277400   CAT   \n",
       "\n",
       "   day      macd    boll_ub    boll_lb     rsi_30      cci_30      dx_30  \\\n",
       "0    2 -0.082603   3.093652   2.454291  42.254789  -80.462511  16.129793   \n",
       "1    2  0.156758  42.707023  40.853199  51.060642   51.523672  10.432018   \n",
       "2    2 -0.935583  18.646867  12.660477  42.554828  -75.437694  25.776759   \n",
       "3    2 -0.279801  32.174381  28.867833  47.440243  156.994917   5.366299   \n",
       "4    2  0.655611  30.348091  25.455647  51.205303   98.374108  26.331746   \n",
       "\n",
       "   close_30_sma  close_60_sma  \\\n",
       "0      2.749560      2.861671   \n",
       "1     41.058033     40.603775   \n",
       "2     15.744065     17.616374   \n",
       "3     30.327211     32.389914   \n",
       "4     26.689551     26.423592   \n",
       "\n",
       "                                            cov_list  \\\n",
       "0  [[0.0013489692418775557, 0.0004284139989242508...   \n",
       "1  [[0.0013489692418775557, 0.0004284139989242508...   \n",
       "2  [[0.0013489692418775557, 0.0004284139989242508...   \n",
       "3  [[0.0013489692418775557, 0.0004284139989242508...   \n",
       "4  [[0.0013489692418775557, 0.0004284139989242508...   \n",
       "\n",
       "                                         return_list  \n",
       "0  tic             AAPL      AMGN       AXP      ...  \n",
       "1  tic             AAPL      AMGN       AXP      ...  \n",
       "2  tic             AAPL      AMGN       AXP      ...  \n",
       "3  tic             AAPL      AMGN       AXP      ...  \n",
       "4  tic             AAPL      AMGN       AXP      ...  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## Add covariance matrix as states\n",
    "# add covariance matrix as states\n",
    "df = df.sort_values(['date', 'tic'], ignore_index=True)\n",
    "df.index = df.date.factorize()[0]\n",
    "\n",
    "cov_list = []\n",
    "return_list = []\n",
    "\n",
    "# look back is one year\n",
    "lookback = 252\n",
    "for i in range(lookback, len(df.index.unique())):\n",
    "    data_lookback = df.loc[i - lookback:i, :]\n",
    "    price_lookback = data_lookback.pivot_table(index='date', columns='tic', values='close')\n",
    "    return_lookback = price_lookback.pct_change().dropna()\n",
    "    return_list.append(return_lookback)\n",
    "\n",
    "    covs = return_lookback.cov().values\n",
    "    cov_list.append(covs)\n",
    "\n",
    "df_cov = pd.DataFrame({'date': df.date.unique()[lookback:], 'cov_list': cov_list, 'return_list': return_list})\n",
    "df = df.merge(df_cov, on='date')\n",
    "df = df.sort_values(['date', 'tic']).reset_index(drop=True)\n",
    "\n",
    "df.shape\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>date</th>\n",
       "      <th>open</th>\n",
       "      <th>high</th>\n",
       "      <th>low</th>\n",
       "      <th>close</th>\n",
       "      <th>volume</th>\n",
       "      <th>tic</th>\n",
       "      <th>day</th>\n",
       "      <th>macd</th>\n",
       "      <th>boll_ub</th>\n",
       "      <th>boll_lb</th>\n",
       "      <th>rsi_30</th>\n",
       "      <th>cci_30</th>\n",
       "      <th>dx_30</th>\n",
       "      <th>close_30_sma</th>\n",
       "      <th>close_60_sma</th>\n",
       "      <th>cov_list</th>\n",
       "      <th>return_list</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2009-01-02</td>\n",
       "      <td>3.067143</td>\n",
       "      <td>3.251429</td>\n",
       "      <td>3.041429</td>\n",
       "      <td>2.747390</td>\n",
       "      <td>746015200</td>\n",
       "      <td>AAPL</td>\n",
       "      <td>4</td>\n",
       "      <td>-0.070153</td>\n",
       "      <td>3.080129</td>\n",
       "      <td>2.452222</td>\n",
       "      <td>45.440187</td>\n",
       "      <td>-32.212994</td>\n",
       "      <td>2.140064</td>\n",
       "      <td>2.750408</td>\n",
       "      <td>2.862473</td>\n",
       "      <td>[[0.0013661507161541254, 0.0004339394370086589...</td>\n",
       "      <td>tic             AAPL      AMGN       AXP      ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2009-01-02</td>\n",
       "      <td>58.590000</td>\n",
       "      <td>59.080002</td>\n",
       "      <td>57.750000</td>\n",
       "      <td>42.737892</td>\n",
       "      <td>6547900</td>\n",
       "      <td>AMGN</td>\n",
       "      <td>4</td>\n",
       "      <td>0.232163</td>\n",
       "      <td>42.852617</td>\n",
       "      <td>40.817726</td>\n",
       "      <td>52.756855</td>\n",
       "      <td>92.828031</td>\n",
       "      <td>0.814217</td>\n",
       "      <td>41.122029</td>\n",
       "      <td>40.691921</td>\n",
       "      <td>[[0.0013661507161541254, 0.0004339394370086589...</td>\n",
       "      <td>tic             AAPL      AMGN       AXP      ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2009-01-02</td>\n",
       "      <td>18.570000</td>\n",
       "      <td>19.520000</td>\n",
       "      <td>18.400000</td>\n",
       "      <td>15.193848</td>\n",
       "      <td>10955700</td>\n",
       "      <td>AXP</td>\n",
       "      <td>4</td>\n",
       "      <td>-0.832049</td>\n",
       "      <td>18.463254</td>\n",
       "      <td>12.644441</td>\n",
       "      <td>43.957537</td>\n",
       "      <td>-42.853088</td>\n",
       "      <td>16.335101</td>\n",
       "      <td>15.742755</td>\n",
       "      <td>17.499519</td>\n",
       "      <td>[[0.0013661507161541254, 0.0004339394370086589...</td>\n",
       "      <td>tic             AAPL      AMGN       AXP      ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2009-01-02</td>\n",
       "      <td>42.799999</td>\n",
       "      <td>45.560001</td>\n",
       "      <td>42.779999</td>\n",
       "      <td>33.941097</td>\n",
       "      <td>7010200</td>\n",
       "      <td>BA</td>\n",
       "      <td>4</td>\n",
       "      <td>-0.002009</td>\n",
       "      <td>32.948625</td>\n",
       "      <td>28.452125</td>\n",
       "      <td>50.822040</td>\n",
       "      <td>272.813028</td>\n",
       "      <td>20.494464</td>\n",
       "      <td>30.469477</td>\n",
       "      <td>32.344130</td>\n",
       "      <td>[[0.0013661507161541254, 0.0004339394370086589...</td>\n",
       "      <td>tic             AAPL      AMGN       AXP      ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>2009-01-02</td>\n",
       "      <td>44.910000</td>\n",
       "      <td>46.980000</td>\n",
       "      <td>44.709999</td>\n",
       "      <td>31.093395</td>\n",
       "      <td>7117200</td>\n",
       "      <td>CAT</td>\n",
       "      <td>4</td>\n",
       "      <td>0.833183</td>\n",
       "      <td>30.850187</td>\n",
       "      <td>25.434766</td>\n",
       "      <td>53.661247</td>\n",
       "      <td>129.524653</td>\n",
       "      <td>34.637448</td>\n",
       "      <td>26.926402</td>\n",
       "      <td>26.424173</td>\n",
       "      <td>[[0.0013661507161541254, 0.0004339394370086589...</td>\n",
       "      <td>tic             AAPL      AMGN       AXP      ...</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         date       open       high        low      close     volume   tic  \\\n",
       "0  2009-01-02   3.067143   3.251429   3.041429   2.747390  746015200  AAPL   \n",
       "0  2009-01-02  58.590000  59.080002  57.750000  42.737892    6547900  AMGN   \n",
       "0  2009-01-02  18.570000  19.520000  18.400000  15.193848   10955700   AXP   \n",
       "0  2009-01-02  42.799999  45.560001  42.779999  33.941097    7010200    BA   \n",
       "0  2009-01-02  44.910000  46.980000  44.709999  31.093395    7117200   CAT   \n",
       "\n",
       "   day      macd    boll_ub    boll_lb     rsi_30      cci_30      dx_30  \\\n",
       "0    4 -0.070153   3.080129   2.452222  45.440187  -32.212994   2.140064   \n",
       "0    4  0.232163  42.852617  40.817726  52.756855   92.828031   0.814217   \n",
       "0    4 -0.832049  18.463254  12.644441  43.957537  -42.853088  16.335101   \n",
       "0    4 -0.002009  32.948625  28.452125  50.822040  272.813028  20.494464   \n",
       "0    4  0.833183  30.850187  25.434766  53.661247  129.524653  34.637448   \n",
       "\n",
       "   close_30_sma  close_60_sma  \\\n",
       "0      2.750408      2.862473   \n",
       "0     41.122029     40.691921   \n",
       "0     15.742755     17.499519   \n",
       "0     30.469477     32.344130   \n",
       "0     26.926402     26.424173   \n",
       "\n",
       "                                            cov_list  \\\n",
       "0  [[0.0013661507161541254, 0.0004339394370086589...   \n",
       "0  [[0.0013661507161541254, 0.0004339394370086589...   \n",
       "0  [[0.0013661507161541254, 0.0004339394370086589...   \n",
       "0  [[0.0013661507161541254, 0.0004339394370086589...   \n",
       "0  [[0.0013661507161541254, 0.0004339394370086589...   \n",
       "\n",
       "                                         return_list  \n",
       "0  tic             AAPL      AMGN       AXP      ...  \n",
       "0  tic             AAPL      AMGN       AXP      ...  \n",
       "0  tic             AAPL      AMGN       AXP      ...  \n",
       "0  tic             AAPL      AMGN       AXP      ...  \n",
       "0  tic             AAPL      AMGN       AXP      ...  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "## Training data split: 2009-01-01 to 2020-07-01\n",
    "train = data_split(df, '2009-01-01', '2020-07-01')\n",
    "#trade = data_split(df, '2020-01-01', config.END_DATE)\n",
    "train.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Stock Dimension: 28, State Space: 28\n"
     ]
    }
   ],
   "source": [
    "stock_dimension = len(train.tic.unique())\n",
    "state_space = stock_dimension\n",
    "print(f\"Stock Dimension: {stock_dimension}, State Space: {state_space}\")\n",
    "\n",
    "env_kwargs = {\n",
    "    \"hmax\": 100, \n",
    "    \"initial_amount\": 1000000, \n",
    "    \"transaction_cost_pct\": 0.001, \n",
    "    \"state_space\": state_space, \n",
    "    \"stock_dim\": stock_dimension, \n",
    "    \"tech_indicator_list\": config.INDICATORS, \n",
    "    \"action_space\": stock_dimension, \n",
    "    \"reward_scaling\": 1e-4\n",
    "    \n",
    "}\n",
    "\n",
    "e_train_gym_random = StockPortfolioEnv(df = train, **env_kwargs)\n",
    "e_train_gym_single_stock_nstep_sarsa = StockPortfolioEnv(df = train, **env_kwargs)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "import random\n",
    "def random_agent(env: StockPortfolioEnv):\n",
    "    env.reset()\n",
    "    terminal = False\n",
    "    while not terminal:\n",
    "        action = [0] * len(env.action_space.sample())\n",
    "        action[random.randint(0,  len(env.action_space.sample()) - 1)] = 1\n",
    "        state, reward, terminal, _, _ = env.step(action)\n",
    "    return env"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=================================\n",
      "begin_total_asset:1000000\n",
      "end_total_asset:5903444.101724851\n",
      "Sharpe:  0.9379218356006198\n",
      "=================================\n"
     ]
    }
   ],
   "source": [
    "env_rand_post_training = random_agent(e_train_gym_random)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from agents.single_stock_tabular import nstep_sarsa_single_stock"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Episode:   0%|          | 0/5 [00:00<?, ?it/s]"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Episode:  20%|██        | 1/5 [00:03<00:14,  3.56s/it]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=================================\n",
      "begin_total_asset:1000000\n",
      "end_total_asset:6255223.506060048\n",
      "Sharpe:  0.9673927897720405\n",
      "=================================\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Episode:  40%|████      | 2/5 [00:07<00:10,  3.57s/it]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=================================\n",
      "begin_total_asset:1000000\n",
      "end_total_asset:6296073.013116989\n",
      "Sharpe:  0.969955838351546\n",
      "=================================\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Episode:  60%|██████    | 3/5 [00:10<00:07,  3.53s/it]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=================================\n",
      "begin_total_asset:1000000\n",
      "end_total_asset:6288529.529650994\n",
      "Sharpe:  0.9703507899959317\n",
      "=================================\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Episode:  80%|████████  | 4/5 [00:14<00:03,  3.56s/it]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=================================\n",
      "begin_total_asset:1000000\n",
      "end_total_asset:6264336.18624744\n",
      "Sharpe:  0.9680922578919282\n",
      "=================================\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                      "
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "=================================\n",
      "begin_total_asset:1000000\n",
      "end_total_asset:6319972.590799077\n",
      "Sharpe:  0.972258290054779\n",
      "=================================\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\r"
     ]
    }
   ],
   "source": [
    "env_nstep_sarsa_post_training, episodes, _ = nstep_sarsa_single_stock(e_train_gym_single_stock_nstep_sarsa, num_episodes=5, gamma=0.99, epsilon=0.1, step_size=0.5, n=40, stock=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7f78b4480e20>]"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAi8AAAGdCAYAAADaPpOnAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/SrBM8AAAACXBIWXMAAA9hAAAPYQGoP6dpAADCGUlEQVR4nO19eZwdRbn2c2YmM5NtspBksm8ECAGyEEgImyiRsIjgcm8EFIiAV4X7KXFjUVY1XK8iXkVRFPFeF1AUUEEEImENW0iAsCQEEhIge0gmySSZZKa/P87p7qrq2rv6nD4z9fALc7q76q23q2t5612qCkEQBPDw8PDw8PDwqBLUVJoBDw8PDw8PDw8TeOHFw8PDw8PDo6rghRcPDw8PDw+PqoIXXjw8PDw8PDyqCl548fDw8PDw8KgqeOHFw8PDw8PDo6rghRcPDw8PDw+PqoIXXjw8PDw8PDyqCnWVZkAHHR0deO+999C7d28UCoVKs+Ph4eHh4eGhgSAIsH37dgwdOhQ1Ne70JVUhvLz33nsYMWJEpdnw8PDw8PDwsMCaNWswfPhwZ/SqQnjp3bs3gOLLNzU1VZgbDw8PDw8PDx20tLRgxIgR0TzuClUhvISmoqamJi+8eHh4eHh4VBlcu3x4h10PDw8PDw+PqoIXXjw8PDw8PDyqCl548fDw8PDw8KgqeOHFw8PDw8PDo6rghRcPDw8PDw+PqoIXXjw8PDw8PDyqCl548fDw8PDw8KgqeOHFw8PDw8PDo6rghRcPDw8PDw+PqoKx8PLYY4/h9NNPx9ChQ1EoFHDPPfco8yxYsACHH344GhoaMG7cONx+++0WrHp4eHh4eHh4WAgvO3fuxKRJk3DzzTdrpV+5ciVOO+00fPCDH8SSJUvw5S9/GRdeeCH++c9/GjPr4eHh4eHh4WF8ttEpp5yCU045RTv9LbfcgjFjxuAHP/gBAODggw/GE088gR/+8IeYNWuWafEeHh4eHh4eXRyZH8y4cOFCzJw5k7o3a9YsfPnLXxbm2bNnD/bs2RNdt7S0ZMVexbB8/XbM/vlCfGh8My48bgwOHiI/cLK1bR9+/eQqHL3/fpgysl/i+fbde/G7Z1bj/Z1tuPP5NTh6//2wclMrJg3vgxs+MdGYvz8+twa3Pv4W/vzFo9HU2A3fuOsl3Pn8GnznY4finOmjjOl5mGH5+u046YePAQDGDuiJtzbtxIQhTbjytINxzLgBqWh3dAS47cmV2Lh9Dxq71eLMKcMwZkBP3Pncavz3P5ejW20Ba7ftxg/+bRJeX9eC/134Nvbs6wAAHNTcG3W1BQzp04hffOYI1NS4PWyNh3XbduP/nl6FjgB49b0WtOzei9vnTEOf7t0SaR98ZR0+93+LqHtNjXWYOqofamsK+NiU4bjsLy9h++59AIDZR4zAAc29MOeYMagtvcuefe244R+v49dPrgIATBjShD9/4Wh0r69N9R579rXjtidWYcP23Tj+gIH44PhBiTRPvbkJD7+6Abv3teP3z6zG+MG9sXpLK04+dDA6OgLs6wgwoFcD3t68E8+//T7OnjYSl50y3vmhdyF++fhb+PZ9r+EzR43C9WceSj37yb/ewPcfXI6vzToIF39wnJTOvvYOfOmOJdi2ay++9ZEJeGDpOsw+cgQG92kU5vnT82vwtbteQqEALPjqCdi+ex/OvvVp1NfV4rPHjsaFx45FfV3RePDu1l049UePY9uuvQCABy89Ho8t34gHlq7Ddz9+GO5d8i6OGN0fHzwoWece1YlCEASBdeZCAXfffTfOPPNMYZoDDzwQc+bMweWXXx7du//++3HaaaehtbUV3bt3T+S55pprcO211ybub9u2rdOcKj36svui3x84cCB+89lp0vS3PvYWvnP/a+jboxuWXHVS4vlX/vgi/vzCO9y8f73kGEwc3teKv/GDe+NHn5qCWTc9Fj179ooTMahJPOh4pAfZPkg0dqvB69fraz55WPT2FnziZwuj68NH9sUvzj0CR3z7YSM6P/rUZJwxeVgqXnQw7/7X8PPH3qLuff4D++OyU8Yn0orqTYU/fX4GjhzdHwDwz1fW4T8YAeisaSMw7+PmiwASD7+6Hhf+7/MAgN4NdXj52qTm+bBr/hkJVrq45dOH4+RDh6TijYcVG7Zj5o1xv3/gy8dh/ODi+LtmSyuO+94j0bMnvvFBDO/XQ0jrvpfW4uLfv0DdO+2wIbj5nMO56de37Mb0786Prgc3NWJdy24qzW3nH4EPjW8GoP/dV91wmlY6D3doaWlBnz59nM/fuYw2uvzyy7Ft27bo35o1ayrNUqbYuUc9WC19bxsAYGvrXu7zp97cJMz77vu77BgD8Pq67dFqJkRrW7s1PY902L23IzWNHXvo7/fC6q3YZfFNl6/fnpoXHezg9I/nVm3JrIyWXck+9vgb4v6li51tcRk72vh93lRwAYAVG3ZY8yTDtl00L2u3xcLDToZ/1Ziwektr4t59L68VpmfHRFZwAZLt2KNrIXOz0eDBg7F+/Xrq3vr169HU1MTVugBAQ0MDGhoasmYtN9BRfan0Y7Ln1qq1iDZNIS09j8qCp2y10b/a62wNy+Hc63BdeMD9Gd9zUBxJwyX72X2HQHjJlqkcnwxHDb0x0Y9EXRmZa15mzJiB+fPnU/ceeughzJgxI+uiqwbOB+KMUW38etDgfb48f1NXwpYMqvd3MVGyE3g1T75sfbluPzrkqrj6PBzAWHjZsWMHlixZgiVLlgAohkIvWbIEq1evBlA0+Zx77rlR+s9//vN466238PWvfx2vv/46fvrTn+KPf/wjLr30Ujdv0Amg0wlV/niy52ld+VhnQD9oVDd4q2CbT5qRj2gCvPbmugmSZfBey0V5HYzFz1U/yu47FISXppqXguEopCPYmWpzPDoXjIWX559/HlOmTMGUKVMAAHPnzsWUKVNw1VVXAQDWrl0bCTIAMGbMGNx333146KGHMGnSJPzgBz/AL3/5Sx8mTaD6umD1cewRgysM5Fgi5bLmeqVvw0PKMvJb4+ZwLUi4MKXz83SmWu/aMPZ5OeGEE6QNgLd77gknnIDFixebFtV1UGUdqsrY9WBQDk2GS+hqitJMTKq8LibnhO9YECC9XrQyMNW8pKVvm4aXp1waQ49skctoo66GPE8cPFQbvx40yqDIcAq+pkjvnnYZFjykLSPHVa5E1iYbHfo2HFRznXvQ8MJLDpD1xJGlf4BH9YGvZcjvR+Vz68ZvJ8qrijZKQVtEJP/9SMxgPjQv5oV6s1HngRdecoA8R3oAyQ6fd3495OjgRhuVnw9d8Nob6/wqSqcLso3zo5vSV1DWETquIWsTWb+LDj2bIvPczj3M4IWXHCDrMSytiTeh7vYDQJUj+9Bjp9D00XFlNnJtkuKVUQ0w2TuqEtpdG9OVj1DqPPDCSw6Q9+6UUBHnnmMPGfgOu/n9prrOuWneoRxmo6xNLa4h0zYl36X8L5PnjRU9socXXnKAvNthk5trVYgRDydwpbUo2w67mgWl07yQZiN7HnTL4F3nDar4K/20FmVraV48ujK88NIFYNrJEwO1HyU6FVyZRcrVLMoRHUVrXtw6A/PK4F27ousKUrNR1g67OtFGORa4PbKHF15ygLw57rHssE5ueeO3qyGtFoDrAGtBs1ztgO9g7OYdeHm55Tnw9Kw2x3dZO2Orw7X2WIdcntusR/bwwksOkLf+lHTG82ajPCFt/Tv7fBU0G2WqjdEsz5hsBjSB7DZdk/GX9WGtWtFGFnT90NV54IWXHCDrDmU6tiV3AmWep2PHIyXS1r+zU6VT8pGmHF2BRrsMhcOui5etPoddyTODtFZlayWyiDbKe6V7aMMLLzlA3jqUaoWYN367GrKof6uw07J57GrdSnc8gMph15oyQaPKVgGyNpF1tFFWDrs5r3IPA3jhJQfIukOZO+yy19mqiD3MkF7zonfPhk4W4E6ijgUMSvOS0SZ1anOsXRkVcdjNONpIh2Ke26xH9vDCSw6Qtw7F2pvzsKeDR4y01e/OYTcdH9rlaO6mG3DSaZcR8H9HtO1JxzSUjvAOCnEIWZtIvkt1OOz6savzwAsvOUDeO5R32M0X0k4Urswi5dqnRPtU6VSb1BFmI85zF5NzclHgRvOSFeQOuwaJHZct5CGjPB75hBdecoC89SeVY2He+PUwg6tInfJtUmd/T7sMio4bh2aTMnnXusgq2kjGUNZmI53QdO/z0rXhhZccIG+rAZWmJW/8djWkDpXmEsjvR9XVsqR6A0XmLMxGee9XZg67rsvWSOPNRl0aXnjJAVzsJumyT6o0LX4AqCzSmmtcaV7KteEXrxieH0yW0UZOQqUVxwPYfteyOewG3J+lazkTpu+W2TtlQ9ajAvDCSw7AG4grCdVx93lzLOxqyELzYvNNy2c20isoTbukHXbdODSzqDbNi6w+sx4TdIQdv8Nu14YXXqoEKru2S7t3UtPCPvcDQCWRtvb5/iIWKviyOexy7nE3qUvjsKsoz5pyjOSW+vLrSiNRx+QYk+BdznzBdKtMjbqwqq+c1bGHPbzwkgPkzQyTZMd77OYJqaONNO8p6VRQ88ItOpXDrtxsVI5TpfO2KJBxk7nDro7wYkE3XzXskQZeeMkBctehVCvE8nHiwUF6s5EbmuVqB7o+Omn4oTUvjp2BOWXoXOsis7ONJPxkHyqd3g/QVR6PfMILLzlA3jqUalWVN367HNIKL9zJ2SZyIx0facrhvkMqzYuivAzeNeP53wHEHGVtStY7HiC/pk6P7OGFlxwgbx1Kvc9LvvjtakgdbeTMqaOSPi+8dGmkl+zfRbUpXXUdD5AtDzrkvOala8MLLzlA3qJ3fLRRvpGXaKNyRcnp8uss2iijBq5aFOStX1U02kijkdsIez7aqPPACy85QN76k0qdnTcH466GbBx286uC578uz2xkz4/qeAAXUEUb5U2hmfi+pF9Q4l0cm4100njNS5eGF15ygWx7lGmHVQ1Mvv9XFmnr35nDbrl8XjT9W7L0eXGBrKKNyuWwS/OX7ZigpXlxXKZHdcELLznAph1tRiuXve20vn7nnn1Yu223MP3WXW048QcL8KHvL8CWnW1K+o8u30hdf+mOJXQCh6PGd+57Faf9z+PYvbcdAHDpnUtw9q1PZ6a67wxIM7ne9PByXP3XVxL3F739vjGtPy16B8+t2mLPDIGr712KE/77EazjtGPe+27e2YbfP7Oaunft35LvpYtr//YqFr65uVheRtMiz2w0++cLMfqy+zD6svsw+bqHrOguXr01PXMcfPVPL1LXn739edzxbLHO//7SWurZzx9902nZWg67AbChZTdGX3afNt1fPbEyBVceeYIXXnKC91v3Sp/36d4t+v325lbq2R+fXyPN+8p7LXhz4068tWknXlyzVckLO2ixcDm43/r4SrzyXgv+uuQ9AMDdi9/FU29uxqtrW5yV0dmQpv5vevgN7v0fzeffV+GGf7xuzQuJ3yx8G6s2t+Luxe8mnokmsivufpm6fvi1Dal4OOvWp4XlfWTikFS0Ab459pmV6YW/Xo11qWnwsGdf0qnpsr8U65wVXl5QCFBZHA8QIMBNhu329qdWGaX3yC+88FIhDG5qpK5Vmpeagnh7y33t8ry0PT+94JGFo2Z7IvLCfRnVhP0H9gQA3PLpqXjjO6fgycs+FD/MsG5G79cDD3z5uOj63Bmj8OwVJ2JAr3pu+s079jgtn9UqAnY+Pk9ffiJevOokzP3wgdznhw3rgxe+9WGcMXlo4lnYX047bAjOP3o0AKCZ6a9WUDjCsxjQqx6vX38ybj77cGm6rA6Vdglj03Xpb78e3YRpOgKgjRGwvvfJiYmx1aNzwgsvFQI7cJn0bdOBgBQ2XAgFXVyuKAvIwbtbbQ2G9e2O2poC9SwL9G7shvraeFjo3q0Wg5oaMbhP5SYEm/cd3KcRfXp0Q4/6Wu7z7vW16N+znlkU0OUN6FUf5XcRpaJ02GWwX88GNHarRff66h+mTR16w/Q96iVaJQ7NpsY6DGpqMCrLozpR/b2iSmG6T0KaaAhy4HUivGSkFvFRTARKVVEgJtfwV5bhnoUCXWYulvUpXreg8GblPQ2Iug+zuxH67cKLjM8FyiFsNS81khmKT7L668pDD154qRBMN35LEw1BrvhcTHtZTZ1edokRVgUlRzicSEUogB7+w4mzkhNoGlOnkmtOArI8l+9tfRyA8lDW/E/Ypl8wXMjwNGNxmuS9KqgKD0fwwkvFIN5DgZuaEkDMhgJa85J+5ssulNQjRDx4x/fCSSrLeioUCtSEEZZfyV2V07S3GtXEz5EMwvJqKM2Lg37DXOsG1MkmcKA6NJa22zXUyoQXTpv0skvXgRdeKgTT3TVJAcTUYbadIO4iAtmbjbJH/J2SZqMs66loNqKvK400ZjKl2YjzOKx70oTmRGOZ6PO6ZqPyw3UbM/2GsdlI/Pa8sawatFAebuCFlwoh6bBrYDZKoXlxMQxnNXX6rV1ihN+4EmYj+rryk0Ga11XNZby5Map7uPUzYgUCbeGlAp+gEmcV8cqXac54PKo0bR6dB154qRDMHXb107rMq6LnEv7AxxiR0yhxLxQkMhVeCFNJ8Tq7snSR5n1V7HOFM0rzkp4Hhmx8rUmzEgKk8yZmrHnR8HnhmY1y0F49ygMvvFQISYddZQ7rsiifF2sqJCdZmY0yIVuVICNeQkQTaYZCXoEtM7OS9JHqbS3MRrGzdCEWGNPwENKtKs2L2zZmq3mRmoF4ZqNctFiPcsALLxVC4rwgxWAh056oJjPS5yWvmhfTd+oqKHB+Z6t5YQQWlbOo4/K575bG50VYUOk5T3gJCLORS80LQ6NdYSclzVflRlm+qwShYCc1G/HoFvwiqKvACy8VgqkKmXLYNeydafKq6LmEH3RixIM3GflTuWijSiKNL5QqUocnGsQOu+Q6PotoI13NS/k/gus+bkuvVuawy2kYOWiuHmWCF14qBVbTYOLzwjxTqUpd7/OSBQoFeoDr6urfWG1O3HQYtisCqW0oXptv8paqfMW+Ky7oFR9IyiPqPox2cXEkhmmEYbTHTpd22JX5vCTrhvXZ8ui88MJLhZAq2iiF5sXv81IdkO1hka3mhTFV5WAiyNJhVxVtxN5LA7bP656cnoNPkBrmO+xqmI18tFGXhhdeKoRU0UaGZbkOQc7OYdeLLyF4mpdoz5FMNS+09JKHuSCV8JJikzrX0UYsdPtlJcxG7jUvhtFGWpoXnoCfhxbrUQ544aVCMI02Ijuqeah0/h12Aa95IRFFvJCb1JVjn5cCv8zKHg9gD6XZS/K4gGyjjXSFUKUAloFw43yBYuywW/zrjwfwEMELLxUCOzgoB7JAeKEEFW3kwvEwK+HFSy8RopUn0UPL4bBbUygIjiSo3MdJo2lSa17E5dVkvM9LuyZRlSkkC01c5X1eSt/AcIbyskvXgRdeKoRUxwMYjgTU8QAOHA8zO9XYCy8R4nDd5J4rmWtecrZ8TWc2UmlexNFGIAS5LIR+Vah0jE4QbWQ4aIWppdFGXNWLUTEeVQwvvFQIyX5n4rBrX5YT9bcDGjxkJhRVIYj5M0I5NqkDyj/+K/c4yvJUaUl5xeMB3O1qnHDS1/Z5SV+2KVy3MGN6tmYjL710GXjhpUJImo0U6UkBpMLRRlnNnV50iUFulBbDXdiuCJUINTVp++I0/ETqs410HXYdaF6Ya1cHM2bRb5ybjSyjjWSaM55Q66ONug688FIhmDvs6qdlUT3HA3jxJUSlNC+ktqFcMGn7wjSCRGpnV3F5breoMzcVh1CZvjLpNrmJNlKnIZE3k6dHdvDCS4XA9jv16tM+Yqg9jeTD5SU9DS5d6nfXFmR4Z7tE/hcZVk1NASiUeVRQH42hfmFRCtUOu3yH3TAvGZ6uZEEDNBFdnxelw64tO1KabqmaHw9Q/Fur2KSOhZddug688FIhmB7SlspsRDrsOjkeIDUJLuh3zKaMakH4negNdrMfmekt8csDVXtKYzZSQXq2UYEQGK2os3Tpa32zkWoHbfedxfneUIY8RpvUSSQ3Hk0vu3QdeOGlQmDNAupIaXvTT9WYjVK8Y6cDR/NSln1eUH7Vu8nu0qZpbKKNSK1X+NSFgGAtvFTA6SUvp0qbm40MC/KoWnjhpUJgd5BUDuAptBIdKfKqeHGJNNqlzobY7yJGfDxAhj4vhfKvXk1MpiKIBAHVu6jOUioU3KleEscDOPqMWbQH1xTNHXaLkGmdvM9L14YXXioAcjDW9WOgw51Nnd9IjYb7qAlrOpLQ0a4tutCmixDhwJyV2a5USu5Wr5k67OoeD5BBv3G1w24Wcn6ljwcAp/3r0MxZ0/XIEF54qQDIgUHlUBjlSXE8ALXDbhbGe0dk0rxjZ0P4+jVcs1F2lVNT0G+TruAiVFoEpcOuJNqohjAbZaGx1HfYLX+0UaUddnntX4em17x0HXjhpQIg+1y4g6TK/k2Oc6b2d3IbchcTn6uVv2zTrq5uNuJ9Y4cWDCEqMfar2776jYWaF0U+3nPKWdphtBErEOgKL6pvkoXDrmuSpmNGFGQgeXceTS+6dB144aUCoM1GeoNjGpOK8x12XWleJNddW3ShTRchXO72KkKhAmYj1etoRRsJqNjs8wKi7l0eD8CS0N5hVzElZ9Ec3LcxQ1N36a/szblmIy+9dBl44aUCIFcM+qtpewmE3mHXLK+Ck3R0GEIdrs1bVYxo8OaYjbIU7dhTpcuBbLWBqn1eOD4vxLPwuQttY9JhN8c+L5U2G0UCpNTpJQF/PEDXgZXwcvPNN2P06NFobGzE9OnT8eyzz0rT33TTTTjooIPQvXt3jBgxApdeeil2795txXBnADkwxJoXee9O47Dr+ngAV4Ol7D26utkoWv0Tt1z6X4hAOqmWC2rNi47ZyE7zwgvFJZ2lszxVWnuHXWPK6eHcYdfS50WueUnCa166DoyFlzvvvBNz587F1VdfjRdeeAGTJk3CrFmzsGHDBm763//+97jssstw9dVX47XXXsOvfvUr3HnnnbjiiitSM1+toB12S/dUeQT5i88UPgPEWThOzEYOaACsj4uPNiIRn+0S3ytHtFHBcO3q2v+bN8nplCFKI3yXWLUlpeXygICEw65qwcJpAzp0XcA1SdsISaniJQgS714oeK1tV4Gx8HLjjTfioosuwpw5czBhwgTccsst6NGjB2677TZu+qeeegrHHHMMzj77bIwePRonnXQSzjrrLKW2pprQtq8D819bj3+9vh5t+8xOzQsnpG2te6XpSO3JO+/vMiqDdAx8f2ebUV4edrXts87b2rYPP3hwGVZvbqUGmY4gwG8Wroqu57+2Hn9e9I423dfXtWDpu9us+coTNu3Yg72lMx3IaIt9JSl0z752AMDe9g48uWITdrW1Oyu7UIFoI7J93rPk3YQjq8y80t4R4Kk3N2HHbn6btDkeYNXm1ihvppoXbYfdCuyw60hCfuatzVi1aScWLNsoTLO1tQ3PvLWZ0p61ltq07Ptt2tGGd7e2UvcqZTZ65q3N+N4Dr+O1tS0VKb8rwkh4aWtrw6JFizBz5syYQE0NZs6ciYULF3LzHH300Vi0aFEkrLz11lu4//77ceqppwrL2bNnD1paWqh/ecY1f3sFF/zmeXz29ufx3ftfU6Ynx5otJWFizu3Paee5+q+vUM/qauSfkRzc7n3xPWnafe1q4ev5t99XphFhwlX/xI//tQLH//cj2LA9Nh3e/tQq/OqJldH1rY+vxFf+9CIWLONr9Ejs3LMPJ9/0OD7y4yecCGeVxhHffjj63a02/rZrthSF1q/f9RIA4IcPLcc5v3wG//HbRc7KbtvXwV3tjh/cxE1f5+AY36fe3BT9XrlpJ/7+Et1GZXPzr554C2ff+gw+9Yunuc9FE/voAT0A8Ff2L67ZCgDYvHNPfLaRmAVtmB4JMmq/ngCA+lp5/y63omHhm5u10i1ZsxWzf/E0Tvj+AmzYvkeY7sM/fAyzf/E07nt5bXRvUWmMkS0GX1yzFU+/tYW6VyjI82SBlt17MfsXT+OnC97EKT96vFOMQdUAI+Fl06ZNaG9vR3NzM3W/ubkZ69at4+Y5++yzcd111+HYY49Ft27dsP/+++OEE06Qmo3mzZuHPn36RP9GjBhhwmbZ8ftnVke/b39qlTK9jTMcmaN3Yx31rGdDLXV9xanjcfqkodGgRy6imns3SsvZ267mTUVDF9t2xdqmFRt2cNPIVmwhthOr7vdbO9fA0b9nfeLe2m1Foe//Fr4NAHhsubqOdDFmQE/uSn/uhw/EBw8aiGF9u+PGf58U3T+wuXfqMlmtyfL126nrsEX+5OwpOH3SUBw8JBak7nh2DQBg9ZZ4BX7ruUdEv0cP6Mkt84pTDwYgX6m/vbnV7fEAzLVIufGxKcNw2mFD8I2TDwIADO/XHf/xgbFiulmYjSQ0n1gRt7ePTBwiTKfSQgzq3QAA2FgSbP75yvroWXNT8VlNTQHfPO1gKl8oMA/v3yNBU+Wz1bO+VvzQEhtaaP/Nd7eaacY97JB5tNGCBQvw3e9+Fz/96U/xwgsv4C9/+Qvuu+8+XH/99cI8l19+ObZt2xb9W7NmTdZslhU2GtlA4hASPpp58CCsuuE0fO74/fHjs6bgE1OHJfKqz5HRiXtyM1pm4fjrzd36WPbtk/FLYqIHgInD+3LTDu3bHb+eMw1PXvYhfPzw4bj+jEOc8aF22C3+3X9gL/z4rCn4438cJc37ofGDot+NdcnJ6qix/dG3R1EoZBVHZF8pFApOT5VO7iidJLrqhtPww9mTcfM5h2PcoN4RH5efcjBW3XAabj778CjtcQcMKNJJz1qSV02qZ08bCQDooSkUXHHqeNz//44rlSEpv/Tw4CG9ceFxY/GxKcOiZ7+ec2QpTZJCTaFACbchzj96NACgvs4H2HYW1KmTxBgwYABqa2uxfv166v769esxePBgbp5vfetb+MxnPoMLL7wQAHDYYYdh586d+NznPocrr7wSNRyTR0NDAxoaGkxYqyqkjaRhcxPDLfMkuQGei91M3QkdjugoHD49+OBpHbTdXZxO6soUZJGUZkh1sjDvfcj3Zp+T5AoELdeOyYCdNofnwJ1FZJ72HjQW7UDHjyiONuK0UYm2TPSkHBs8epQXRmJofX09pk6divnz50f3Ojo6MH/+fMyYMYObp7W1NSGg1NYWpfSuGg5r89ay3Wd5G5oB8aqSOh7AAW/uhA5HGhzJlUcMtr557iq6LiwuN2/TPZQ0dN4keeTlpCd41XM6AUmvhgqVziDayMI1g3z32gx9U3XfNtwh3KQdxE644jzxN+flp9OQEAnftQ6FbY98wEjzAgBz587FeeedhyOOOALTpk3DTTfdhJ07d2LOnDkAgHPPPRfDhg3DvHnzAACnn346brzxRkyZMgXTp0/HihUr8K1vfQunn356JMR0Ndh0IHKVxpqdqO3MCYQd2eRoAZ3VoKvoBmfHDHSI68YjBls3/CgWvRnR7eZtqud0+yZX3vxjFArc3/E9dVlhXpeRV+wEb9ePYn50jxaxgS7N0JfYpB3wxiUW0lDpKD9XdOXSy7KuPCoDY+Fl9uzZ2LhxI6666iqsW7cOkydPxgMPPBA58a5evZrStHzzm99EoVDAN7/5Tbz77rsYOHAgTj/9dHznO99x9xbVBiufFzI7X9fAdvRCRmYjd8qNyqm7uyJY7QF3XtCcq12GEKuIsO2b5JG3zwd1zaFnZDaSTpRmkO0orQu+2SgNV3yYmo1MunK82aJE8xKlFZuNVFo3+r63G3U2GAsvAHDJJZfgkksu4T5bsGABXUBdHa6++mpcffXVNkV1StgMhNITl0s32FUib+DVdC+I8gec6yx8VVzRcb2teWcCWzN8fxA9ON28TfU8SsDZUI4VXpjnSrMRk4NqPxIhyQZJjak5DZJbmfkkPfSIRjuEG7QDHTlCpnmRmfJE7Vd3M1CP6oF3va4AUvu8COiJVp3UIKm5qyeQFIZ0jzLQhZaSR2dreJlg5xEhqaXgmVQ0zUYuN29TagPpiUzGIss/3yk5vpeMNqLzutVupDcb0bybCw660GXNToBS16mMnMxjRmTmcz12eVQeXnipAGw6UCC8IBx2mYE62k7exGGXSFCbEF70aOhCK7LJkI4fm8TQmeR0HXaz3Lwt8bz0N3bYFUcbsfzz3kcWjUQKFDUFcqLMwGxk0VjJ96mpcSlY0dAlWWPRDmKBR2I2Cmj6VH7JQCQSbKO60ubSI+/wwksFYKd5iXMJT6dlNS9htJEkLwtq8GZaRziQOHO0deQc3GHwfl0ZOlWj7fNS+uuivlXtiW3eJIsJJ+REJ0jSk5mNyMi8rA9mZI9B0AHJe5YRNPoOu+aOsDrarMhJWyJ8cp21RQ67BXM+PfINL7xUADb9R2o24ssusWObgWaCfMwOBM7NRjqaF0faGQ9N4UU32sjlPi+q5wmzEelxI3d64Tt8Er8Tmhc6r41mQYTk8QDmNMj3cRmuzkLfbGTeDmRmHzDPZE7lvPxCzUum/kEelYAXXioAnRNTE3k4+dlnCXs/h75JtFHCh8a12UhrN18NOt5spAWtSc5Q81JOs1E4cZMs2jjsysKf6R129SJjdMEKK1Y0SbNRhaKNyGc2R1tp7Z0TLsgksdIm7+3NRp0PXnipAGSrCmEeScRQ+IwdSHj0latcYjfTpCZHk4guHGleSEI+2kgMPc2LHlxu3qZCpFnkOOyypWuFSnMEgBCU5iVjs5GVwy7526FWiIWsH1HaWcVuxzzIQp3Z8qXRRhwKNQJpSmNfPI8qgxdeKgCZM5owDyc/C5YaryMrBxiCt2TotdvoBj0qGtoZr3nRgk7V6LZJp5u3KZukxGzE5BVFyNGI77GPaZ+XQpQ2Cw2T3Q67McPhBnHlPh6AcuqvEX8LEbSOB5BoXiLfO079iVplreOxy6Py8MJLBSBbVYggUznHzm2MsMErW9F3w3IKHALRvjGOTpzXcsbVKIuk4h3yxNCpG9NN6tw47MppdHAmsvgnnVfHbEQ77Ip5KQCZapjSnm0UO8u64iiGXLCIH5IRibrvo9N2RLuGk/e4+7wI2m+WdeVRGXjhpQIQhTZrZeJcihx2eeR1T5WWmY3Keaq0TllGm/B1Ybh02DWhqaShmYAymZT+qo48UDvssmYj2ufFrcMufW1nNiIFuDyYjfj3ZdDhmzUV0vmLf3mCiKj9ZnmIpUdl4IWXCiDqPpYOu+y1iB6vI+s67JIbdEX0HDsI6pAxjUjyY5MEOsKLtubFXVswNRvR5cs1L8pQaeY5G20kEpJs4OJsI9pfJyRcbrNR/LDGxmwUZZCUEaXlCZ+hFkVf8+J32O188MJLBRBuGmfmsMteB4lnouMBqHyqcqLMZYg20hjtzAUcPzyJoKPF0nbYNaCpgu6p0pTWIcorYCy85LwQ2U8SZiPBPi8uBATWBJr+eIAsNS+SZ8RD+oRvM7ORVLtjrXnho1KRWR7ZwQsvFYRZqDRjNuI8E5l5qHyqsFTC1iw0GznqrK42qfPHA+iBVzeqyV8Ep1E4Ss0LXaasfJ0+wNPghBD6vMhZ1EJC85JSesl2Qpb5oyR54PHBbW8BEW0kWZCBGdN4/IhOFOelpYQsxxXmh5zKwAsvFYBNtFFy1ZacsFlyPPq6ZiNptJGjzq8VbWFoNvIOeWLoCIKm0UZuhBc5Ed5uq9HRF0xeNsKO9z6yU6XZaCPRRGsDlobNDrvk+9QI6sAFZKyJzj/TZSP8RHKH3SR9tkxe/QnNRhbmLV34BVNl4IWXCkCkKZHnYa4pP4+QngOzESEIJYUhPRq60NOqqMGrC48keDWjo6ngwanZyMAPiy2fLT7xPlzVC/mT1bwweTVMHLpgKaQ1G8Wh0rYcyaA26RR5IIQCNvJLZPIRjCPcPWMKyWeyaKUCkzbik6SdZCsVfPh1ZeCFlwpAtoeBOI+5fdjKbEQJVvypzd3xABrCi6nZKBVHnRta0UaabTLLzdtUZVLlJ9IwArzh8QDUDrvE8QBOtgeQmkn0wD9V2j1MtSgmeXS0WZGpkJdf0vZE7Vd2mGdasG3Dr5/KAy+8VACyPQx0QWkbSn8T/ZZnNtKkWygUMnfY1Vl5mmterNnp9NBy2NVulO4mTpmvBC1MkKXzBWkdzYvUYZfRvAgdgy0gPFDVADoRVy4go0gfoWCu0dBpY7IFnjTaSKPMrDUvXhNTHnjhpQKImraJwy47wHOcVF1sUkeuePLgsKu3Fwz52w8cQuhoXjRJudy8TeqMTgkTSdNBUvOiLo8ON9Z02HXynnT56aON0nIkho5WhOVB/3gAdR4dzQtv/BD5bNn45uhCx1HZwz288FIB2DjsJgb4IPmMpcZ12FWGpZZoFcSh1676po7Dop7mhaOG8khAp2p0zUZZbt4m+pw1HKEjEW3E8M932BVdsA67fLOTLcJ2GvpftKc0G4X+JuWONhL7vOhBR5CIzmvjzFCRwy/PlCf4XDLfHNfwQ1B54IWXiiAWEHTBzvPkqiPePp1Ow6Ovst2TW7GLopdcqandhUqT6VMw1Mnh9HiAiKY9PyGSp6STbZv2QWHLTziJMrT5TqMysxFtEsnCtyeMfLEJleZpjcodbUSWRwkimr4f5DuIeOc5aRMUAPCFvzxEG/kjSsoDL7xUAIwjvWYesWo9JJiINjJnDaRglbnZyFmoNGFC8+seIbQcdjVpudy8jaUg9GEqJH8njwdgrjnl0Q67rNmIT89lVJVOqLAItNkoQ4ddWbQRhwdeHhENcpwSlaJzqrSJz4uNY7EuWD687FIeeOGlAoht3yZmI+aao1rX0byoN6kr5eXw5/pUadMN6IRpRJOdBwWXZiOnm7clzEZ8YZRyVo0T0HwltgvgzX7cnwCSbTJ2Dk2SMUWkeSnY06SjjUp0M7EbSR4Rz2RCgZAtDUFC9koyuVkr2sixuJek5gehcsALLxWAVbRRQnohfgo0ObyOrOpWOoKVq7FSyxlXJ43gtwcNnUlOW/PicvM2mT8X8ZunMVHtLcJ7HyraiEmQiF5y6bAb+nGkML9SmpfQ5yU1Z0koljgxD5JoI6HsQgovglTSaCPJ2FQJzUtCK+4HobLACy8VgKxjCvMkrpOr06SmRFy2ireaQtJZzqX9H9BzWDQVcPwmdWLoVI2uE3kW5pToWpCuhqt1EKcBBGYHSXp21+fYtyY9WLORqx12s5BepNFGpEBJCQV6qhcth12Egh4vv5g3rWgjcXYr6AptHm7hhZcKIBZe9PMk94hI/k6uOpMFqEw18fMCRwWvR0MXOoO3Xjg1Ich1pZHD0KlJy+dF12HX4eZtbDMIqLYtMBtp+nvwV+7830CyTRYcCgjhhBxGvrRbmY3i3+EOu9k47Ippsk7N8X02HT8/WeWiYqIxjbvJoETzInhERhu5rq+Ew66PGigLvPBSAVgdDyDzCxB0dK7mRbOcQiGZ37WDoKtTpcmxoks57Bq+qsu6caqRkDh60mYjwtxT+pvwUdHoVLLJj22TLo/EYLdISKslrNSp0rpOzaL30zEbIUim5eXXRZb7vLC11YVGoIrCCy8psGzddpz0w0eN84k0L6Mvuw8Pv7o+kb6jI8DqLa3UvY079kS/X1j9Ppcer49v3L4Hoy+7Dz9dsILgJ8BV9y7FDf94Hf96fX2ULrEKjTLw38sUOguU19a2KNOQA+CLa7alYckZdu9tx5fuWIxfPbFSK/2r77Xg4t+9gDfWb9dK/x//9zy279lnxNP/LnxbmUZf81L868RMJ9G8fOPPLyXKpMvn8yUDT4MTYu4fX+SmZYWkXW3tuPTOJXhg6Tp1gaB5FR0qqQMe729vbsWfnl+DL/5uEd7f2WZMkwfZd1309vs0T6W/G1r2UPfveG4NNz8pPL6xfkf0+28vvoej583Hh76/AM+u2kLR1oXo+1P3HUsX7DimM2Z5pIcXXlLghw8tx3Ki8+mC1JSccNBA6tmF//t8Iv0jyzYk7j2/Kh5AunerBVAUOEgsXr1VyMP3HlgW/X57cyv+d+HbuOXRN/H9B5dH9995fxeVpxLRRuMG9VITIsisYYS8SuGhV9fj3iXv4fq/v6qV/oybn8B9L6/Fh3/4mFb6f76SFHJVIAWpCUOaAACHDGui0oQTS31dcWg4/gC6fbLpXCDhM0C0i7+/tDb63a2WHK745a/Zsot7nwQpsAzt00g9W9eyO/p94vhBUTlsU/3FY2/h7sXv4vO/XaQsL0TY3kWbrF103BglDbLe+3TvFv3+2l0v4f6X1+H3z67W5kcG8nUvOJbma+WmndR1OHmzQs3r65KC+NRR/aK2BQBn3Pwk9fy9bbvxFkE//FQnTWgGABw+sq9QQOnVUIduNTX4yMQhAIC+PeL6GdKne/TbebQRQ27FBvM5wcMcdZVmoJqxlhjoQowd2FOZj3RG++W5R2Dclf+Qpt+2a2/iHtmB60qj4bQx/ak0O9v0Vub7NB0XZCGKujhkaBNeea+4MtHxeRnCTC48kFTqat1Nqmmww1ArspfjAPHnLxxNXX/3Y4fhirtfTsVXiN9eOB1AcVA/YFAvvFEacEMn7WevOBFrt+3GwUOauPlFDrM2kO5hVMLwft0pvwWR0+bhI/sm7j19+YlYtXknPvWLpwHQfWfqqH74yxePxsd/+lQi3/Sx+0VaTXbC27A92fd1Efu8FGlOGNKE73zsUBw2rI8yL+lEz+sb7ALGGsTrXnnqwThx/CCc/ctnqCRHjOoHoFjnL6zeqtR6HXfAABw+sp9RoEKY9uRDB+PPX5iB/Qf2QmtbeyLdff/vWPTtUY+amgI+NH4Q/v6fx2L0gJ5Y37Ibu9racQCxCMo62ogWsj2yghdeHEOnW5Lq47raGkwb0x/PrtyiRX9Y3+54d+suxmG3eFHPdBrdQULbv8yBw65qd83u3Wqxa288OOnIVbSDpzVruQO5cgSA7vXuBsX+Peuj3+MI4SVc2fftUY++Peq5eUsJAbhxfpQ57IYY3q87dS1q2uR7hRjcp5G/RwyKfeTwkf3Qr0c3vN8aLxJ61tdSad0IacW/8UnVxRvd6mowZWQ/LRqk5sXkeBFThN914vA+qKkp4NDhScFqcEl4Kmo1tiodVScN72skuABx/RcKBUwdVVyc7dpLa9dqawo4ZGjMX6FQwKElQbDXwKLQQgoYzh12mWu/w2554EXECoBt2ibdOVp5URt58Qnp0tXtay4cBFWCRmLfDZ1N6gQOntUO9vu5NNVQdCXRN8I8WZ4qXaJKnyjNOKOLzw9W3lUdGUBexyc3C4ozQKRxZaKETL4qfTxAep5EYPeO4hUV1ZmmU7ONrCU7VTqETj3YnH6tC+3N+TycwgsvFQB5+CH5Vwc8AUK8SZ0mP5rd2cUqVBQGy5bBSy9CZ4020tm3x0k5nCgeZR6HDrvsNwu/p2g/Ed616j69qy5vQuRfuxQQEpoXSUSNCGTSmgyll3hBRAtxPF50xwUbbvlCE5vGjHLmm9R1ojEoz/DCSwUQNu144aLf+Xin6cb02NWpJj+afc3Flhc8oYsug+Zap6zOeqp02bx3rDQvRWSieQmFF7I8Ta2i6D5vgzsqn0B6iY8HcCGk0bwEuda80LzJhAjdPXdspG/VJoP8G3JaWR8P4DUv5YEXXtKA00pNJttwYFT1ad4KlN7nhT8I6tqXtYWXSD9s3ztJvnkOuzaal0Dwu5JwMYAltQ0ZmY0kV8I8Ge7uCh2zkaAuhBoZZZn8WhCFZNu8dmQmKtFsj66NxJf4V4Y+L4kFlkSIiDUv8lqx0rxwpSY7ulE655oX5toteQ8BvPBSAbDbhJs43tUyKmeKHrudvyZN3VVlvOeFJmEOyKK40Uasz4uh9NKZnOXYdpHVSlulleDnKf5147AbUDRDkmTz0DUbifqSaqJn35s1yThZrZdIhH04PIrA5LuSaWuzFF6ib1Kg/tK8hM/CPHKaNg7GvO+mcwSErHzXTv26m/N5uIUXXtJAYgeWgTXzqDof+TwMs6S1DbQmJ86XzeCWZiCnnWuTdNiBSUuTlUOHXWoXUUdMlcdhV1fzUvzr0mwUte3IbERoXjQnLFvNi8gsJdwMT0GPh5BE/J78fisDWQ+1Wfq8CPzoaGZonlTjgpXDrsY93frLzGzkHXYrAi+8VABaA4MAcfRDcsLWXZ2K+FGB529jCuNoI43CyHDqPI4btvVl+z2NyxH81snlMgqHnQTpowHY0gUaFtF91QJBIPi73II/dtQPNQDmAwH1rbKTXTTNRgWKp0wcdnkLREuNpMuT0El4n5fKwAsvFUDADFomGhJeRxV1Fl2q2tFGmupheVkxtKKNDGnmUWVry5GtA3aacrQddh2uYlkzqo5QqxNVRN+Wv5ha8+LSYbf4t8NcdmEcdsuheSlQf7m8aGrhMtO8GHqZux4h2HHMRxuVB154qQDYQcukT/OjjfiOf641L06ijajNonhlMGYjHZcX3p43OYLtxJccpNPzoipHWwVf+utG81IE27blmhc5X4n7ipFOVNcuV+uxbw+teTELlY4TZyq8gB6k5A67enVkY8bmlisQNJW0Sn+dL3C82agi8MJLBRAfDxCqpvXz1kQ+L0mzUcLpUDfaSLPseJBK4/MSg6d5Yd/BVPOSR+nFlqWkY2I2k5WN5sWFCTFE5PPCmo2Imks6L/MZFTrsKngQb1JX4lGRXwexY31JeOmgxwEd0P5vDpgSQCeoIOGwm4HPC6/cRD+oQJslkTwV3aMc8MJLJcD4qJhMSuHRPbxoo6TdXo+mabSRK58X/tlGNNM6vKk2vqs0bHmyXWGmKcfYbOTCnBJqJGpoSUEWbSQ0DwnvW5qNGB7TIBbSin/bbTQv1LfKTvMS7/5L+7XweNEdF2wczmXlytJwaTkYv3hg6eVxDOqM8MJLBRA5w0kGBhHkZiM6rWqwCAdkfbNRUutjCtUZI4nxWKuopBYqT7B22GWvs9K8WJSRxfEAjOzCCAyMYC7ky+x+9JztO8zCwmWzis82Cnkz0bwQWjKHPInLo/9yn2lqZK2ar8RcFUJ3p+FIEM042sirXsoDL7xUAGx0kEmnruEIEMKgBQXduNNpal4S+cxBO9eKy4jTqwvrrMcD2G7GZVwMuZo3zOMy2oj1BaFEl4RwITAPCe/LeRCdnRTmUx06qAN27xT2mBAdsIJmVsqX5BjF1YFQaTKJNuI6CusJsqJ8rhc4SYddj3LACy8VQFLjYG7zpjUv9DNdqvEK17BsveT8MhUmnmSotBnNzqV5sTMDpinHtAyX0Ubs5OLSYVflVyLUvIQ8SnPrgT3LyEYeYgXNrARa0d5RPF50xwWraCMNzYu+trAI10NEQvGSx0GoE8ILLxUAG11h4rDL25iK3T8ihGrADjgrXBlc2P/JyY7n85LYpE5HeCG1UNacuQXPrGcKWwds43KIUUC3DKcOu6W/oQMqTyGo67Bra1oT0Xd5DELYDsI+3M5oYnRA74ZcyKxNiPaOonkJ0+i1BRteZY7CIcy1hdmajfIyBnV2eOGlAkhzqnQtE6kAiPeLUNEN8+mqxF2oXckN5XT2eTF12M3jqsfW4mAbVWFRknERabQHLMJvHEUbla7Jby/SjIj40r0fPVfcd+nbw/Zhe7NRdtq4WEsk0bwwPntZOKrKfG1kafi0QrNkSqYSoAm6p+/BgxdeKgDWzGPjsEf5jjDPorRKPiw1L5rpVSAFmagMVvOiQUflR1MJkK/hbJ8Xe3bk5VAzomked6oXtm3LfF6EfAnvm0kvyUgaB+axiHY4iYamGQMk5NmsNC9q3szNRua8mhmEVOWHvzLWvORlEOrk8MJLJRBpSmiHNx1wD0ETDDSqwYLnWyAvm14Z20AVbZRMb0Yzj8OGLU+6TqppQcsuutOFe7NRZL6K2iWheUn4/4jMRvwyTDUvYXq3xwOENIt/dbQbLBL+SRlJtCI/OpoXhidVtJEFHzqaF/3jAYrIeI+6XI5BnRFeeKkA2NDm1NFG4NPRJavtk+HA/E/m1dkGXqe0vJuNnDnsOuCFW06B/1snj5tJnfb94EUb6UZeic88kiOptaSv3ZhE+O9p8l3pb5WV3gXEAkvGC734ysJhl8eBrSN7FmHvAKdt5G8I6pTwwksFEO3vwDoFaoCneYlXdHqrUzafoezi8GDGruGwa8sUu6V9Vs6ZNlvOx+3QnTkl9nkB9ZdbvmDkEt5XvFfSObr4VzcMWAcdTD+NfV5M+j+heUF2bYINX+choZ1SLCLsHHbV93RFOK7W2gGSskteRqHODS+8VACRpoT5q4ek6UZ0Oq3aYTd0jNQsOVJ323dOMi8v2ojl2XyHXWvWMoP1DrvsdWbLbHGZqpRuHHaLf9mjL2SCkXjCMjMnieixCwuXGqYwqspqh132OqM2wYZ183kRa6e4ezhZ8KpzqrQ+XVrj5QosNZ4vn4d7eOGlAkhGGxlMGRwVrWiTOhXVWPGi15ld+DnQZiOO8CJJL6SZQ7MR5bBrTaM8ZiO6TLN0To8HYFbGMsrm0UbyFxOZXKPbLn17mKgXW7ORaV4TxJ9VrXnhjUk6fVsHvDym41yULjPNC03Qa17KAy+8VABpNC88003s82K2IjE9HkCkkjeBakM5m1Ol836WiKtoo3JIL8anSjsok53UI6FaQtxM72IB1iTicDO+dDvsmpmGbSE6coTmheaJNybRGcx51QuVNm2z2Y4XOR+OOg288FIBsDuKGg1e0SqHVNHyHf+UZxsxf5Vlc0xW5uCYu6gyRKl1KOZn4FAO5BpIrrLzYzdyuXlbIlQ6ctiVSS925iExOb6WKzaV2tElwQorsebF3m6UteZFRj+peVGYjSz40DoewFhbaMGIBP54gMrACy9pwOkFemYOWthQmncIojLTTXJFokdXVxhxMV+RRXFPlWZ41uKNEhTyMXSoBnIdlOt4AJJX0/1U3MguArMRJZXyy0/yZVdJSV+SAnU/aRowB6t5abfZpI41R2bWJpLlJXmh60jVD+18XtykAbIT/pP7vGRSjAcDL7y4hsFcGx8PYO7zQs77oeSfjDZS8GFoNmLLswGZV0vzolWfBM2cOMtRh0Xamo2YysgqssSmDDbcNw3Cb1YbOexCSVu0t4fJURtUvkRkV+mHewVT4ogPo/7PXGd3PAB/TKF4CU1rNcm2wPt0NryKspBVaBpt5NxhNyG8eOmlHPDCSxpwepaRg6mm6oWkaXKqtPYmdboOu5yQSFPQTn3J54lQadN9XnKieSGZcmY2ykh2oTY+083jUAXPhuVyhWpNPwdbHxDhqdICTadNKUKBwEjzQn+rzLRxkSlPwktUR3Qe9nec3hzCfXvIejA0dfpN6joHrISXm2++GaNHj0ZjYyOmT5+OZ599Vpp+69atuPjiizFkyBA0NDTgwAMPxP3332/FcN6hI3XHJ7ai9FclZFB2o5AIQY95xr/k8BHSVyQUF20M1T4v7EBkaDXKjcrWBU/l2qSOKsOwELeOrCFNNVzXhUhQJFf4aVfUscaVKSsFzex8XsIxSq154WmnsjYbFQS/deB6iEiYFPMyCHVy1JlmuPPOOzF37lzccsstmD59Om666SbMmjULy5Ytw6BBgxLp29ra8OEPfxiDBg3CXXfdhWHDhuHtt99G3759XfCfO5hoXliHNx2aPAFCZ6Dh82FmNnKxyRO9P03yOfsOptFGeRk2XGiDyqV5ocrQjTZyqnkpgt3sTBptJJrULOtI6ENDEAyCdN+A9XnhlWGK7KKNwgIkZUd/kxoNvubFndmIvK9rjnIZ3k/Ca14qA2PNy4033oiLLroIc+bMwYQJE3DLLbegR48euO2227jpb7vtNmzZsgX33HMPjjnmGIwePRof+MAHMGnSpNTMlxvbdu3Fmi2t0fV7W3cl0oj6xZotrdGOmh2MsCHrevvaO7B+2+7oOhysdu9tj8uMnqnegOGV+atCWPamHXusBwCe0EWXwaY3Mxvtaxc7vWzbtRcbWnYLn8vQsnsv1hvkpc5bErzCtl17FRuxqe/ooKMjwGtrW7TSmqrg9+zrsGoL21r3Rr/ZST0+HkBWNwJzgq0uQiBQkHdJbkhn862tbVp1sKvUZ1n/GpeaF1cT87pSW5fxJo024mYw50PrO2u32eLfLTvbjHgIgoBqr7zn9LU+7d1727FtF592EARYs6UV7+9sw7Zde7Fy0068b8h7Z4aR8NLW1oZFixZh5syZMYGaGsycORMLFy7k5vnrX/+KGTNm4OKLL0ZzczMOPfRQfPe730V7ezs3PQDs2bMHLS0t1L9K4533WzHp2gdx3Pcewc8WvImfLliBjdv3aOW98u6Xcdz3HsHYK4qmsuv//ioAYOFbmwHIVw5zbn8OP3hoeXQddpT/Xfh2JAyBGfxDdO9WK+Xru/e9RtFUgaR3/H8/opUnAaKox9/YlHjcu5FWBpqajV5YvZWbZvOOPZh07YOY9t35+P0zqzUYjfHu1l2YeM2DmP7d+fjpghVaeZ5YsZnLX4iX39mGSdc+iC/89gU8t2qLFk1bZ9SxV9yPU370uPA56UCqK7yQvFz8+xeM+PnRw29g0nUP4q5F75TulHxBmNGI/PZNjd2oZ++83wpbdKtNDnu72/jjERXdQzB0x3Nrot+Tr3sI15X6tAi/eWoVQZOuZJPvSiatKRQS3+s3C9/WJybAY8s34uePvqWdnn9kiRshSlQ3pKCkK4yEjuEX/OZ5vLF+uzYP1//9NUy67kE8+Mo67vNv/Pllhjc9dHQEmHXTY5gxbz427UjOJZ/51bM47nuPYMr1D2HStQ/ig99fgCnXP4TVm+3bfmeCkfCyadMmtLe3o7m5mbrf3NyMdev4H/att97CXXfdhfb2dtx///341re+hR/84Af49re/LSxn3rx56NOnT/RvxIgRJmxmgvteWhv9/umCFfjJv/iTWI/6pMDwO2ay3LSD7myyCYOd4EkBZfe+4oAbaXIYOhd/cJyYMIC/LH63lD/57FsfmUBdTxrRF589dkx0vWZLUuukA5Wn/43/PhmHDG2KrrXGQCJR3x7duEmWEYPVFXe/zE0jwt9ffC/6/b0HlmnlGdTUEP3u4FTwbU+uBAA88Mo6/PQRfluqYyZZVyaCH31qMnV9+qQhGNm/Bz5++DA01MkF3ogXYhq9/2V+3xfhhw8XhfEr/lL8DmH1RNFGpWuyrXzu+LEUjfe28bVgA3rXC8s9/+jRGDuwJ/79yOR4sn47Te+dkoaVfE9ZU/z1k6skT+MFS5EmDZPv2rOhDh8/fBhOmzgEzU0NibFk3KBe2rREuPKeuH/s2RdrMscP7k2l29dOa5BVJuHeDfHCZPKIvlq8jBnQk3t/bzup+RJrRUhs3x2nW7Fhh1YeIO6rN/zjda30uoLb7n3teHtzK1rb2rGcI0w9sSK5uAOANzfp896ZkXm0UUdHBwYNGoRf/OIXmDp1KmbPno0rr7wSt9xyizDP5Zdfjm3btkX/1qxZI0xbCexrD6KOG+Lo/fezpkeOXXWKZRhvnIvMRsz9fj3FAzmfQoxTDxtMXd978TFoajR2kdIoKcbR+++HEf174L7/dxx+ds7hpfQ6DtDE75wYnNPy8eEJzYl7rrwbDhnah7qeOqo/Hvv6B3Hjv0/WpuHS1YKNwonONio9b2qsS0xiw/t159KaNrq/sJxrPnoI/vWVE3Bgc29hmhAnHlzy36M0L8psQuwjZnNWCDCtyhv/fTJuPvtwFAoFfPqokdQz1/4cJG/fOGU89WxCaZHB3f+Jw8bQvvE3++TU4cqyrzz14IQAHyKtkJblMKH7Caw/VU7GuErDaDYaMGAAamtrsX79eur++vXrMXjwYG6eIUOGoFu3bqitjVd0Bx98MNatW4e2tjbU1ycn2IaGBjQ0NCTu5xnpHBj1hy9eSp2wRhl0netcrPy1I5sM6pPUbOTH01/t8yIDr6ZdCQy25icSLt1EY58tvsOuzdlfaRGWSUUbOZo1Eu+TgueEg7s9KT59iWNsciM/kg+5P1s59iySIcthQred2MsueRnjKgsjzUt9fT2mTp2K+fPnR/c6Ojowf/58zJgxg5vnmGOOwYoVK9BB7B62fPlyDBkyhCu4VCsi1alFwzLbYTOZOBDqXvTA45jHk4vxRr9+wvrUocn/XUmkjTbi1r8jkcGJ+cmp5qX4N7mJGN8cKoejOgr/MtFGLpAQAlLwnKgbxx1AtgdQdC3Ze0pIq7KyS6YCgL7mxTLoIS+DXIVhbDaaO3cubr31VvzmN7/Ba6+9hi984QvYuXMn5syZAwA499xzcfnll0fpv/CFL2DLli340pe+hOXLl+O+++7Dd7/7XVx88cXu3iIHSKN5MenHtAMh/dd2Rc0daLiTZ3qYa17Moo3yIr2owkZV4K1MnWkVHNBwuXIOq6dWoHkxKcuFVgkQRBs5alusJSQNz8lNHd2CJC/a8ZnrsKui5YY9a2SqedEVXjKm39lh7MQwe/ZsbNy4EVdddRXWrVuHyZMn44EHHoiceFevXo0aImxgxIgR+Oc//4lLL70UEydOxLBhw/ClL30J3/jGN9y9RQ4QDnZZn3DMcyC0Ua+T4G/TX2GzUemvzoF4ZJK8nDCtOgZBhaw0X67oODUbhT4vieMBzMty5dTM24PJ1Wrd9BgPE7hu/9IddsM6Qjj2xc9U2yBUWvOS5TihSzuwPMokL2NcpWHlgXnJJZfgkksu4T5bsGBB4t6MGTPw9NNP2xRVNYjsvlmXwwndFJ0qrQtts5ElfbosvRqKnTc1aOZxkzrBb11whUdnJpH0dFxujpbQHIaaFwuzkSuuIrMRuVioArNROee12LQWlR49U21AWZYT0isE3U9gKwznZYyrNPzZRo5QKJP0Qqmxmb/2Drs8zQunbBc+L4ZmI9PROC+LkrRmI94H6LSaF/ZsozDaKKq3SjjsJum5alqJTeqcOuyWrwPEmpdS2QYOu5XWvGQ6TmQcbZSXMa7S8MKLI1RG80L/dbma4a2sXfg5aLvrhnZ0jbT08QD56NlBSt1LVsKjKzpuQ6WLf0XHA5hpXtxqp8iyXanrXZqNyql5SdYtXUcq3zNaeKms9JKpw27G0UZe91KEF14cgT0RN+tyioWFf2yiMggyHJZdOT4my9KrH9Fpvnya/N8VhYInVT3wBEVXTrIuJo5MzEY1tN9YrJEx4csNT6F2pCxmoxRMs3VTzhDgsOwoxF1xPAD53pU2GuXCYddHG6WCF14cIeyXOg6mLsoplhVQZdqOgfoOu3b06bI0E0b1qRFtRP4WJS9zh6cdds3zZ+Vz5IpOFk6mtYy2zUaj6I6vpObFVRuqZSSONCyzgk859zmKIrI4Yx8/VJrMmx1fOshynNbV0NnykPUcUy3wwoszJFcfWZZTLKv0N6XZiNvXuD4X5RtxTFxedPZUKXd/pzXoPPu/vC5zbzZKTyJCWDu5Mhsx/hyAy2gjflk2YLOWs52zTs1kP+QuiHLl85Kl2Ug3HTVwGdD30gvghRdnSLPPi005xbJol11rs5GinOieHfm4HIPKMYo20tjNttyq1rSmLL5w49afIxUNp04vNM24VZfatRFfbliKI2ncm43Yukv1PcpoNkoUzTg1K0+VzlG0Uab+uvrSSwQTbYo3GxXhhRdHsAyOsS4H4GherH1eeGYjTtkpxxuTurHdpE5sNSpvj9cyZUmQpeYlf8cDML4t0RYApbIMXty1doqsq1w67GYQbWQaERhxQAns+da8ZDkcWMguRt/Nyy5FeOFFE2xDYxtbms6ocNIXpw3oe9ZmI869LKKNlO9GJDB5F2qfF8HIW37NC7kKTRau3JsmQ58XF4SchM0zIdFh++pg2jU3r+ChK9NpHG2UNNOmRcJslIJWFtFGulpDNiJLJbDTPi/qt5ZN6DZmH1thgZdfnlAvpa12Nj/nt1UWXnhxhHiXyfI1rLARh2XaHw+Q5JlHK+18ZVI3sROgmeZFpH4t966Uac1GmUYbOZBeXB4PELXfaIddpl0bjFKuouR4dJxFG7EOuw6jjVw4c2pHBEbaKb2xL0/RRtk67OqmU5nZ+PCySxFeeNEEtWoo/UciHGDTmghUnTobsxGvHPfSi6puKLWyZh5A1y+mvFAeUqcYyE3NRiarsYqr7EuIDzMtopbpQzJHdNE72L4bm4/6PhyfjjSozdBs5KKlkxRkvCUjnfi/ebR03lkmZNsIfNTY6ciUy4PNPi8m/dc77BbhhRdHSHOqtC3iQT42HFnR4dzjO+ymNRuZTLAGDrsBe83JVXazEVm0eeGm9W/kT2TMDYeGS39dxmwUv0vgvCwbsD4dadX2eT8eQNvnJeIh2VdV2y9U3mE3uwHBZp8Xr3kxhxdeXCFyMC1fkZHPQMiCQ80LD7l12GW6Pl92qS6zkek+O2YmufQTh8vJJ+ScjTCLNS/lB1lFIr5skfdQad2+wjrsqibjPDns5mOTOvK3gebFCy8AvPDiDFEHLmOZTKS09SCvOockhEs/BxVM6pO1MfPylN1hVxk2KodpVZuU4STayGVTCGgNS3TgaFRW+Wc6SkvA+F+lbUrJUOlUxKhLF86c+poXmcOuyv/FgjGHyHI4sKFt5LBrQb8zwgsvjpBUeWcPRnaxFi54PPNopR1vzDQvnBFRkzBv4KzsPi88fuQMcaO9JCO+mdkoXw67kc+Lg03qXIGsanYTtrQCArvDruy7qpA4HsCakjmNsOwaTl/l0aDfs9LSS5ZmI02fF0vtrI82KsILL45gYuaQwSR3R0nl0MGsXI3LLNM+L5lFGyXKSVe2C5A8lON4ACOzmAvNS3oSEaLjAQTRRpU2G4GZm9NGqtSyp0qnoMUKoh0Owmi0x7DQbMTpq+pQaTveXCHLaCPd6vPRRunghRdHcGU20tmzJJkn5MGlwy5P85LWYVcfJvWZcNjl7atiULYbBILfRbg+HsDGnygNsnDYLQg1LxUwG3GiwWJzVrrWlHifND4vWWheTM1GnHzKTeoseXOFbI8H0By3yd8+2sgYXnhxhHjgdad5UZGKBvmUURmqVZL8pkk55k6leqHSrNmIV7Z20U6Q2mE3g2ivmI4DGi7NRqX6Ca0KsTm0gpoX4rfozCVbOI02Ym84aOe6JKLXiBya5ZoE2o+o0tFGGdLWJO6jjdLBCy+O4E7zQvxWpWV2KLUvU75Kkt0zKscgrcneGnoq4PL2eLneRY0so43K6XitA9ZnK4ilcgAVMjFwImOcbVLnMtooE82LHpUC89dkn5eKO+xmaTaySGemefEAvPDiDCaaAhUi9bSCGDPGWzv+6ZqNUh8PYOGWoaV5Yc1GudC8yO3/NtEYeTIbuURYF/EOu6D+VkLY4u0G62qxwL5Pmok8uVGcA58XzXTh9+IdoqqKYKx0G8xW82Jm7md/m+TryvDCiyOYOJiqEJJQaRQ6GCHHdjzQdV5LH21UHrMR7xtk6aDHA+2wa164qc+RmT9RvqSXsHrYaKNyO1mToJ1Ls+XL5SZ1Ltq5rtMvYzVSCuy52qQu02gjcx5MuKlkv8gTvPDiCFFXdGhzVplMonQp1eumZ5nYwk7zoiW9yC5L9ypoNuKq0M0rs7MdDxCCPVU61jwWryvjsEv8Lv1lNUIuaPOujWgxQoCTU6V1yw6jjcJ8CoGdF8FVKeTPbOSefmeHF14cwWRbEhXYwVucji4z69VMOaONeKpoXbr52OeFXFXZaF4492TlGZeQH0QOuwKzUWVcXpLSi64514g20r1fFscD6DemAsWDUmAX/K4Esj0ewMJsZMKP17wA8MKLM8QbWZVv5ROmjMxGDqONeEiveTHXDuj5vNCJ+JqXCsKicL7DrsRs1GFAu9IzB4NISGG+edp2nQbS4wEc0ubfMKDFXJdTdok1L3pjH33YZaXNRhnS1k4nN7Olpd/Z4YUXR4hOlXZASzckM6F5sRVeNLkuZ7RRnEedK3E8ACdLuXelVEWN2Tjsyhw7TVZuuYs2KtVF5PMSCuWl55Xgl3uqtKZGVAWXDruJunFhttZ8wbBsXc1LTYH/uxLIcjTQ93khfmdAv7PDCy8W4E8Uxd7owpkqpKGi1cEIObZmHX2H3XQjjt0Ou+q0yWijypuNyHe1c9jl3MvRqdIuETnslma0jo7wfgU1L5zfrEbImjbr8+LUYdfF+KNZdsRDOPbFz7jRRjly2M3S6VWXNr0jsT4/3mG3CC+8KNDREeArf3wR8/7xenRv994OtLXTenqXe0Gs2LCjSEuRLkBANfq8m40u//PL2mnZ82RkYAfK1rb2RJpHlm3QKvePz6/BUys2AQB+/8xqPPPW5kSa79z3KrbsbJPSeerNON+9S97TKpsEV60u1bzwsXPPPj3aKbFpxx7rdG9t2gkg5uvdrbtKf3cX77tg0BB0WC9tNrr9qVXSvOu27cbPFryJ90tt5L//+Tr13KHVKAE3ZiMzTWzI/mPLN8Y0xOs7Kq8t9rYb2Ek5YPlbsmYrbn9yZUKIWLZue2raIuzZF7/DXYve0aZvw1NnhBdeFFj41mb8+QV1w9p/YC8AdoPHqP16UNcf+fETAIC3N+9MpD1kaJ/odxDQHYU3HkwZ2Tf6PXF4n8TzZ1duEQ5Wx4zbDwAwfUx/ALFa3wYrNmzH/NflAsRRY/eLfsdFqWuUHSxufGh5Io2OALH03W34+l0v4exfPoNn3tqMK+5+GbN/8TQa6uhucuvjK/HTR1YI6ezeSwtPvIGJFCB6NXZLPH9xzdbEPZYPEqKV2/0vr6Wu62oKmajsb3o4Wec8fPD7C6LfPRtqqbDcpsa66Hfbvg48XRIA32/dm6BzwkEDufT79qjX4oPFMfsPoK5pLUERQVD8Ljc9/IaU1jm/fBr/9cDruPSPS7D03W24+ZE3qee9iPck6dsgi31eDmzuHf0eNyj+PbRvd7rsEue9ifd5a2Nx4cXTDpDttzdTB1w+BvcWPnt7c2v0OxynVGjZnRTkQ5x585O45m+v4v6X11H3T/nRY1q0bfBmaZEKAI+/sYl6JgtXX8IZG7oivPCiwPqW3dLnw/p2x7fPPBQnTWgu3uC0uTEDelLXQ/o0AgD+56wpAIBzpo/C3A8fmMjXRkjmBw9pwrNXnohPTB0W3QsCujjeivonZx+O4w4YgB/OnoTfzJmG6844BNedcUj0fPWW1sTk/6vzjgAA3Hz24bjujENwy6enAihGg5x/9GgAQN8eyQlXhm27xAPHuTNG4aqPTMAFx46J7qU5pfu5VVukz/cf2JN7/73Sih8A3t4SD46N3WoTad/cuCNxLwS5otLBqP49Evfeb01qdnh8hBCNdaTm5YSDBuI3n52WieZFdzW4nZhAjt5/ADXJHTMuFiD2dXSgR33xfY8Y3S9B54pTD+bSH9CrQYsPFlefPoG65mteArzz/i6o8ObG4qJjwbKNVJsCgPOPHo3BTY3CskyRhcPujP1jYeDC4+I+GS7QorJLhZ9w0KDoXqj1DPkY3q87bpo9Gb8+/0iq/R42rA+OGJX8riG+/2+TcPwBA4TPSQH8vz4xUZiOBNk2RELeGxvodqxjQgsFsUtnHiilzaIbe0IngXYJjabuZmNvZ4UXXlLiOx87FJ8+ahTqamlnQxLsijls7AN6FleJPRvqcNFxYxP5Qkoj+nfHP750HAb1bkRDXS0G9W6IyqLMRhz+hvXtjv+7YDo+NmU4+vWsx7kzRmPyiL5xGUT+2UeMwKobTsOJBxcFsb49iun79YxXs6dPGgIA6GPcgcSd8YDm3vjssWPQsyFejZmEnrOrPJVNuK6G3+wDwYVx9JKWnw5h71b4B5D4wIF8jYNIexbe/cjEIbh9zjRKQKg0amoKFNe1xIxECuYHDEquwHvUJ1fuZ00bYc3LoKZGfPGE/aNryucl9L/qoOt5ZqmfmGDamP4J4TGNMJllqPRFx41BE6MVHM/RhtTX1UQLMjbYoFAAzpwyDB8cP4jKUygU8FlisQKAqv9PTh0uj64jfg/vlxT+eRjeL9YciepJVn+iR+FCrn/PbtJ0SXrilNLv6F1eAHjhJTVCDUENx2mNhyAIojS8iAY2LUmbLTMI6PJ0ozLYdKGKUid77Jznrgfxig3v6ZSTdNhlr82EGxV9FUzp89qM8XwmKDKknbcII6BYT2RdkTySz8oVmUKWTx61EZmNmEq24cv02Ac1vWTmtKajDsG4w97j/Y6/p5hGHuByx+3QwTxsM9oOuxIFrYyGd9gtwgsvKZHcZVLesIp+KklhgS+80LTZtMXVqcLpRYFCIV79agkvDG8GJUl4EN+zcdhVCjMiPgQXfM2IjB8zcDf0EnwM0TcSlVnJiB0lGJ8tSvMS/c+E93QvKSqHbIv0ychWpXDuuNO8AOm1L1F+haDFLZuhIXuzNI7LNjVWUPRpFQ+qMtnjLVRgk2lvbqdHvtPDCy8pEQ08mmaOgEhDqaY5XSMWKhg1c/Q8oB12NXu0SNWso752eQBlRFOie9Hp0Mr9cBLp02tG5PyoM5B1bSoc8ctUlGdIrxyQaTJIs1G5wmp5piJZ+TZ8yQR1G/Cypu2asnoXCS/sXjg87XKe4HL8YjXk2mYjdnPNgP9bla+rwgsvKZHcZVKePiBGZbXZKKTNlskvS3eYEJ2HopM/i6GI9+7ROTca+VXCic4OvPICDM1MxvSTt0zHfKHPS44nkUS0HL00Lr/WiOyPREuPz1wSJtcvQvOePkH3ZiPSXyVRnGCvFtZHzeaw2HLOyS6LYjXX1poX6rfEH0aXsU4OL7ykRNg5dQcySvNCre44aRW61wCSwV8CseZFP69L6Z/vB6AvvajMQgkSppoUs+TGgzAvuenEKNIOmQim5QZr9qQ0L9q7jVAUU/Ej1LwI/LyshBdOpvxpXsRtRqh5YRZvQfwgn3A4foWkYv8eO+lFdSq3zrOuBC+8pEQ4GJGOabKJnfR5obfLFpuNEg674VEEQSAc/GVg6Zmo501Vo8lSkuCqp5W5CMoS9Sv3WoOmLL8yvdbeNAH3dwhTR0dRm8u15oUxeyaijRKTQragHVCTz9katqlT/rEP9u/Hd9i1Jkfl59EuCOoo/h0oaeQBbjUvRWph+9XXvIg1wjISXnYpwgsvKcE67AJyH4kOItoIHLUrm5alXbwOV4J0Wbo2+KTmxVw97yKiJmaIc6ugXw6bRBU6bR5tZJreKDk/2siMhLDM2PfAkGAZUGy/pPBdIJ7F0UaVcNjlmkRYzUvKMlxANm7YQjYeFARX7BEBNhq/crZRlxE7UUSfabSRZNyS0fA+L0V44SUleGYjZcQRkoMDdxUnmHjia7vjAdhkOpEBbBnG2ghJer4fgP4qRraCMeWFB3OHXXUaymHXhd1IxEvuzUYxGJcXrmN7lhCbjWKeqPQW38j0tHA1PfeQ1bvYbFTKG9B/8yg0A3baKVGWWMskT6fiQd9hV7OATg4vvKREOPCQg5JU5RfoCwsicw45UNi044TmJRKm1CNNJFQYlikT6GR+AHomGMNrQ+6N39WYfjK9K81LvicRJloOjEBXZpOXMFRaIEhbcaXUZhiS4615HJmNeMQLgt9RtGVAm40qfQCjCDZVJB7DQjeAdGYjDkkKNQZjYleAF15SIurflOZFnJ6086sGZdHEQx4UZxMqzQ6Xdg67umWV0kueyTbu0tO8yO+o9oFR0s/YbMRLb+6wKy80j5MIKaAAxXcmhVaehlJBMRU/dPQfz7eDMRtZVKlKm2FOj+PzkrIe5A67/DqKFlQsDYN3K2u0UZaaF03iUs0Lp7Q0R6Z0RnjhJSXCBstGSohANjyVg61II0JN7BQ9vZGCLVek4eHnZYcpPUjNRlzhRV/Dw07cppqY6L7wwgw6WVUDnLHDrqIcwYkIFUWx+RJmTxDvTWooK6B5IfsI688RpzHnS7VrrSmy1LzweRX9pifWPDuKA3YCnmrcMN7nRcITr6waQ4fgzo4cDmnVhpLZSOXDUALliKgQFiJnS26Jye3VdYcJdkAxcYyMHWk1CytBajaSRRtZqF5UDrqZO+AaVg5Pa2JuNuKXyXMOzwto5/Xi4B+3bbHDuhjp3pF3kjT524XZiC+oWxCK8iYzp3VGlTl5K/d5Cc1GURp9lFPOsakiUb2G942jjRLjlLys2kiI9tIL4IWX1OBFG8nNRvpmGpHXP7lJXcC5r0IilUBIkuU1FgBkNB2bjUyvozIFF1nbmF2YjVQq7TwugIv+X4TwzZqNysy70IFeZA6wMhvJ/UjM6SWRvrVKhEaqjsjbtNYh18dSwHz8KuaR34+1T7ZmI0LzwklfrjO+qgVeeEmJyOXFwGykOxlGqxdWeCHKUZ0qzUPSYbeIGo3eIYq8UMF0rDBxDDbe50WLaPwz82gjF9ONUKVtqr0oHxirJwqFAuUca2LOdAFK25KUXZLRRhZ8cSfznJqN1KHSST46c7SRmBYtqGmbjdhxi3qWTO99Xmh44SUluNFGssYVGHTsSCPC93lBQvOiZJdLz2wrb7sOJJugeRojE+e3hGYlGV6kzQsvjct35aZ3MhjxieR5EgmCIPnuxARQUc0LcV80aThz2DUnI+fBmfDC0RIJNC9x0QH110TAK6vDrk0eAYPR4s842oilTz7jmJIL4mddEV54SYlwkmX3qBCB3BNX5agXpmQVIqRjGB1tpCl+sJoXAwO1qUd9ogwJTQoGqxiFrKIdbUTe7lAMJCb88NPEiUw1OzyIjwcoIr87ndKrVrp98dt/ViDriHfumJtN6niCuv0L8nfmTtegZJFC9C7Eyd+s5iWvpg6X0Ubhg8jnRVezLrNnc0iY+tR0dnjhJSXClQXZ0WUOVR2EnV81ZnV0hIXwE3YEgTYtEmza2DFYx2xk14FkdcL3A9AvRxVtlNzJUk2TWgU5fFduegfSi9gen1+zUQeheYnMr8R3N2mXriHz5+ClsaGbho4MaZuTrN5FmpfYkb+keQk4iRQop3xt4/SqctgNBTjd+pcFFvBo1Bru4NvZ4YWXlIgddvXMRgE1YKs0L2E6tkyeX4A+2NWfyZ4MIvu/CrL0qgFdvWMxc62MLuLTK1Ap7AcI05wuBqNKnypttZIlTKjhwE/6TqgOJnUNet8SnubFQRma97Tp8TQvKRmV+7wo6gj03zwKzbZQaWxrbAdHTja+2YgvRHdVeOHFEQr0zCdEQDy2jjYiaVlMTmxKkzlCpEJXQpJcNaAri1KajZhrQ82LqWbE1GHXhdlI5bCbNWwEMNJ5nY3aI82r5ZoAyXJk/hypylD4kRjT49xLy2WaU6XDws3PpSovrKKNhLSKf2tSmo1Up0pHVemlFwBeeEkNbqi0xMeCXFGq+rVY8xLSCqQDjQiiAUXH9m59PIDUYZd3j9BkGdJWRhsp6LFpXAxz8pPGszQbFf9mPYnYvAEVDs3sl0RqZSqxSR0tyLjzNVBpM1zQS82nZpvhCXuRw255lWbGsGqvigVC7K+lywMzbgl+h7CN9Oys8MKLAqqGyA66vDxU5Aq5olRqXsJ0dEKyEaednAJDvxlbFbosvSzaqJhXYTZiHid8YBLCjcDEIkjDSy7jiJtesspq52RQCSMsRJqPWADOqdkovEhoXmxMD+mGdZHmJWyLHUFA92WL4rjvkkrzwjEbpXbYFdPm7X9D/ozrJEimF5QTXRuwnVb4MO1fxWeCPsaM07q8yRZZvLJifzAvvgBeeFFC1UzCbdfJyTbpiEXQC2IzhPpsI1qij8okNkOK1bP2I6BoJ18eWMc80zK4NLn39M0qSWGFhsqBl0uTSOTiXWUU2l3YjYS88NuQa9hOJlFfKN0j21e5jzYg9zniRhs5KMN9tFHyXtq5TWby4R0JUExbKOWlechrtJGVmVN0v/TAdAdcttsrzUZR39Ai3+nhhRcFVFIuV/MioWHiZCtaAZGrHBv1LO1oV4hXajpmI0unMdNTpckXUq0kVf64Mq2HDvirIEl6Y7NR8p7oU4juC8mn1Mxpw2oyiPNE5lee2Uh/+0VjHkS56d+x9MJzUjUqQ97UndBLK7zIzHXCOmJ84XQ0fiJzuA5s6kxnOwsZD2KNbfG+8fEAMrMRh0a8RYaXXgAvvCihNBtpDB5Uo0RATCgqzUtYCL9Qspw0k5ORw26UybAMHZrkPcpsZEY7OSjINTM8Psg0PLOOlB9OctlqKdNoo9LfrP1GbFaDpIDCRhuRBtayOX2q9nlx4bArL9YJRXdmI0XJVHQWnVc4duUEVmZOBS3T7yg1G0m+obcaFeGFFwVUA4HMaY0gEv800rwE3HSUX4Dx6pRXThFaDruWA7nc54VzLwVt1bUO62QeF8cDsPVFRxs5EF4EJMq1z4vVKb1ItnGeVrFcEGteinDjsMvzI0lDL3kvveZFT2ikxz56QWV+qGa5YdFeRX2s9JccP+2imfTMRl54KcILLwqYaF5EWomA+a07OIgkem60keUoQe07o0HDZPM4piQxTa5tnRwIzGirZBUd1sk0psIF32wkTu9mh12B5qVMK2A7h12y7dHmV0owr0S0EfXbts1zyuDes38/Xs60bOprXnh8MGYjg1cr56Rs215l983GrCQ9WvOSRF7DzisFL7wooGqD5MBKbttP0aB8XkyOB+Cn4x0PYOv0Rw41OhSicEDTcqSaF/lq1NTnRbVJnWm0URb7vKShz6WnuJ/18QC2anh2oiTDTUXHY2QF0db3tk7qPPC3BbCnxz0eILXqpURbUfHcsS+gecjtsRQuzUalv7U1yXsmPIjGnxCmp1Z3dlgJLzfffDNGjx6NxsZGTJ8+Hc8++6xWvjvuuAOFQgFnnnmmTbEVgVLzQv4WDHKJaCPNxqfcpC4IUqtngyCIjiHQGmcsB/JyRhslvfj1eeHlcWI2ktAw9anRLRMon/re5g06yL4QMVgoPQvKfjwAry+T911MGcrwY1N6GZiNdNsMVXY0LkjSmNDLGLabKsruk4KaDv3EsSVUhGMyfUHyrCvCWHi58847MXfuXFx99dV44YUXMGnSJMyaNQsbNmyQ5lu1ahW++tWv4rjjjrNmthJQNULeluJJiZq2ZeqaaUT+LKTtM6JsbTYi/A50fF4szUamp0rTDrsKzYuqbMn3oMoUpDENZeaajSRcuhmM5GajrCcGq9UgYTbiHQ9QtkgpyMtxaTbi0k+TNxOfFwlxsmzO7+QmdTnVvNjk4VQsec/YbCTlIvksNql66QWwEF5uvPFGXHTRRZgzZw4mTJiAW265BT169MBtt90mzNPe3o5zzjkH1157LcaOHZuK4XJDaTbiXCTNRiQ9cpM6ldlIpHnh+AUo+BSXYTbY2fvWSGiq8qagXczPmo0UBJk0Lk7QTq5I0zn36ZRJlZfHTeqI/0eh0tEzu92j04DdQiC+HyKbSSOVw24m0Ua6mpekaS3hsJtP2cWZ2YikQwkvGt9AFljAddiVPOuKMBJe2trasGjRIsycOTMmUFODmTNnYuHChcJ81113HQYNGoQLLrhAq5w9e/agpaWF+lcxKDUv8e+2fUX7y6V3LhGS+PKdS+IVpYTuQ6+uFxdNDBQvvbO1xIfdKHH5X17Ga+uK9at3PEAMk0n3n6+sE9NU+AFMvOZB7G3voJ5f+JvnMfqy+zD6svvw6PKNXLr3vbQWoy+7Dx/47wXUfR7XHR0BPvd/i6Lref94PX5mMFj88vG3cMbNTybuv715J3X98Kvro9+Pv7FJm36dYMe2mx5+A8d/7xE88npRA3rNX1/BEd9+CLc/tQpA9pPIsvXbsWTNVqM8L72zDTNvfAwAsLV1LwBGq1hmzQtvx1gg7hcLlm3Exb9/QZh9X3sHbnp4uUWxqaSXBJa+m2681K13WvNC+/vlfYL98wvvRGYacmz524vvCfO0trVjV1s7dW8x0ebZ7R0eWLoWx3/vkWiMJtHeEeBH89+g7tE7sSdRV8v3qeThd8+8jQ9+fwHWbGnVSF2dMBJeNm3ahPb2djQ3N1P3m5ubsW4df3J64okn8Ktf/Qq33nqrdjnz5s1Dnz59on8jRowwYdMpVA2luakxce/ZlVuE6Rev3ko4IopHhx88uEzojBs7zQZYu203AGDbrr0KTmMM7N1AXYeDnc4kYaoa5aU99bDB1LO+3esT6etr6ab5GCGgBEGAh19bz2aJcPqkoQCAa//2ioCZ5K1NO/cI6Zn4pHz7vte496/5K83L6AE9o98DejWwyfGNk8dz6Vx43BjUcRwpn1ixCau3tGLO7c8BAG5/ahU27WiLnrcYtA9dnD19JM3bb55X5unfM/mtSdCr1yJEgvkFx46RXptifakvAcDuvcQkVSr+jufWUOmPPWAgzpoWj03vbt2Fmx5mJyQaowf0AAAcf+DA6N5Bg3tb83xgczLvmvfTTVghz6rFDOXgXOqu7CZ1MhrHHDAg+v2lEw/AWdOK7enkQwaLskT4n7OmAACuPn2CMm2IK049mLp+dW1x3FtNTPC88ZzEsvXbqevzb4v9PWuZfvn5376A1Vtauf3i+VXJOYKneenerTa6d+6M0Yl0Ilx591Ks3LQT1/39VXXiKkVdlsS3b9+Oz3zmM7j11lsxYMAAdYYSLr/8csydOze6bmlpqZgAwzaUcYN6YcWGHQCAkyY0o5FoXCKIHErZfv3bC6bj0796BgCwffc+oeo1XOV0BPFg8e9HDFfyEYLtZDFdNUheOoIANZqrxlBg+8qHD8QxBwzA/S/Hwu6gpuTkzU5YpN+JqPOeN2MUfrPwbQwqCWebdvAFEp4fk2xACOu4qbEOLbv3iRMyOHbcADyxoqhV2bOvQ5gupP+7C6fj4CFNaOxWgx71/K551Nj9sPiqD+Pff/40Xlurv8I+fFQ/7bS6+M6Zh2L0fj3w3fuLWqo9e9sVOYApI/pi/uti/7jYKVHtjP6tj0zAJR8ch16NdWjvCLT6ogxkE+CbjWh8dNJQfHTSUPzh2aJQI3PUHtG/Ox669AMRj7+ZcyTWbtuN3o116N3YzZrnYX2745VrZ2FfR4Br//YK/vLCu+72eVGko52aab8gne0gmhq74fXrT8aefR3o071YB69ffzIa6tRr6o9MHIoTxzeje73+Nz9ydH985cMH4gcPLefyCiTHxv4967FlZ7wIYLXNO9vi8YDMS44xuzn9grcgIvOEv3s21GHxVR/Gnn0dWFcSrk003m2ScafaYSS8DBgwALW1tVi/nl71rl+/HoMHJ6XlN998E6tWrcLpp58e3esohbbU1dVh2bJl2H///RP5Ghoa0NCQnNAqAbahkB2rQXOwTNo2+YMDK1NEK08mHbXPSymRSCAxgck+LyR/Ogj57Nujm3DTPW1agvs1zPbconQq2zWLOBrLjFMy1FTmNByfP1RQaiYAoHdjsg5VyGKvlEKhwNWayaD0ISOcY2PzhZj3fqX6Sim3FMsR/VZUXa+GOuzYs0/kMg0AaO7dSAlXhUIBQ/t2t+SURs+G4jAenq2T2ufFwlzHbl4pGrtYNHarperFRAA1EVxkeXQWLtE1+5z4zZqNTEFmIb9BWEfrW3ZzeeiqMDIb1dfXY+rUqZg/f350r6OjA/Pnz8eMGTMS6cePH4+XX34ZS5Ysif599KMfxQc/+EEsWbKkouYgXchC/3T7tnB7etUsLhi86T1QTLkRQ8v2btlByQiGxGRkyLpo5cGe/SEObeRoXiRDQrvGKpLPj5g+LxQ7S9+OzEg7+naJdNCfAF1BuEmdgoPYkZK3mk7Sywqs06wt4npXvDfncVLzklOPXQI8oYH3jPucuOaZPI34IM1GHKdpWTvrijA2G82dOxfnnXcejjjiCEybNg033XQTdu7ciTlz5gAAzj33XAwbNgzz5s1DY2MjDj30UCp/3759ASBxP69gm4nNwWyiBp88cJG+Fh8PwFud6vEig5bmRTIhy0C+i+h99GnxUaM5eBtrXjTV6El+CDUyo72lhRc7+ibIag5xpTWL6BFaRVgKjbbgRc9olR9pHZIoZ8iwqzKCmGnt8thw8rRRkOUET2jgPQtTiJD2eACSNm9cL0jaWVeEsfAye/ZsbNy4EVdddRXWrVuHyZMn44EHHoiceFevXo2acp1hXwawjVB0JLyUhuA+a+mhVuqESUikeSHDSV3sQqqzSkrrsFtTKAgdkE1pJXjTJMT1TZCkD6MSTHcLla3EyOuIfoZbyWa106kpXVWboXaPtizDFiJti67jKr9dlU8AowS/FNCtd3ospPPGitb8iy+yM4VkW/izqJX0dy0+OJnonZ7F7awrwsph95JLLsEll1zCfbZgwQJp3ttvv92myPxAw5GPhWgwSQol9LVI5Rym6+iA011IdSiQaUw6EfkuovfRp8UvOBw8dHa3DIKAKle2Rb+t6p8VRtnyQ0RmKTPyRsiKtmmdqDd9LP4ld48u1/Jd1IeUIcPRc445sqxmo7D9p6PToVntPKfm8JuVPcw9BXhaUN6z4nMxHXLNHlj4yXZw+OCZjVwcU9EZ0HlUJBmBbScF4YU+DVF2WkVYkJiNSnQJ4nk3G0HwLqJ7NpCtgBPcGAledt4Xsvosu89LVmYjx3Rju375TQ+27xJPKslnuv4jLuDM50VzTKEmVsamUe4NBtOAFAZEPi+xSVrTbGShe+FpgGhTprcbkfDCiwKslGviyBdC1NZUfqui1QsVbSTIawM9zUs6sxFf86JPR1Yuuf+NkoYmTcB+t1BZXdEDlcuvKOYmG6puzUYVPVVawZMwn8xsVEa/nXhR42Z209c4JcuuVs1LclygTcaymrU1qevwATCLVg8vvKjANhR6taFJQ2Q2Yh12GXqiVRvZiF0O8FpnG1GaF32Q76JyVFbTkpvh9DQvjHpY8jZRqDSVXg2Zlqqral5UEyuleWHuZQ3RuyjNJ6W/3DOtymo2osu0ha6Tsex4gHg7iCqQXkgINS/qscV2bIzykMILR+h15dPUWeCFFwUSZiMbnxfRgwQBUnKP9eZCH5HA3SoLsHGc1S+bjGBIDOQa5ZIliTUv6tURj56MJsAPldZ5dTJ94qRrkn6HuYrd9KuXYwrRqndVIlKrWO5oI7L/EW+j6hcyoSE2n5TBbAT99i+DzMlYTJsuOxI8q0B20Yk2inYQtog24uaQtBXyMU/Tb7No7IzwwosCbGMl+6JuFITIGVQWbQTEE54oOqe4C6kZL1IYRhuZOAaSfKaNNhI5rOnYpUU0ZE5wvFWkjtOc7PBFXv4so2ryEm2kqreQXkdATBwViDai76cxG8lpu4SrlbnNpozkmFTkIbyff+mF3jCSfkZuIFlKLAQ5jtk4TfM0L3S0Ec1TV4cXXhRg2wmvMSlpCO6roo3E+y3w/AL0eJFBy+fF1HbCJC2wNKBprtIo1kRtLnLM4yEWvNR0KX5k9DkFmnxD089dDrORThFKn5cwHbENQPnMRqRWVV/DGj6XHTtRDr8d0uSWBrJ6F72FyGxUDVajDo7QEF2X/tYSQrUIhUKB2sYius9NnLxFCy/JZDZmwSqofmt44cUUHBukEoLGprKeiGz+ZCN2OcBrRRsRv402qSNMABZWI4YW/36afRD0HHZJTYqaJjVhaQhLWZoWMhNejP2VFPRi6SWu47KZjQT3Nc1GPJTzFWJn53TSi82CKHGqdHQ//5CaeJi6kNVtAcT72oxBXLMRuVh2YxbsLPDCiwKsyacguRJBpSngXRcKBfEmdRHdING50kBnIjKdwJP55e+tBUW5WtFGOqqQEto5yy2dMmSaF55qP1OH3ayijRx/O3ISDJh7lYPCbBTyzHk320g1Gzhz2A3pGdR7LHQWc3cIxq48gqwuUVQge24aD8WxzV7AUGpeYqY84IUXJdh2wvP+VtLQjTZirvU0L+G99IOEjlnE0mrERDDI31tJSxhtRJdlQkOWh7cSNXfY5aujy4bMNC9mUEYbkW27zA67Img77PK9MItp3LLE58ORw67Ngoh1CdE9mToPkIdKF//WagglhUI8kllpf6lykw1HR/vTleCFFwVkPi+6PhA2mhcy2iLp2EusTh0O8FpmI4ZHXZARDOz7GIfbCoo1ijYy8Hlp5xwPoPPqsvS8/NXosGsqNOvv8xIP0ZV2+lQVr3M8QDnewZ3mhT/uyMvm10GGJ144BEflwTyJ309euezhsEZccMxX9HxjbxbvjPDCiwKJaCNSEtZcV4i8w1XmE6HZKBqk4mgjN8cDmJmNjKKNiAgG2SnZWrSEmiz5cxkNWR6e6l8r2oj4zbYjXv5szUYZ0XX07SJ6UTo734sskGYzyrJGG0Vlppvd4n5tYDaK8gYlHkr3K/3xJOAJe6Joo9qaZFo+UT4dHfjjAczghRcFEvu8kFEI2mYj/v28nSqtO1bZqC/Lcao06expSkPLbKTBA82QmD6vPFfjfDn9aRy7vFCCeV5MD7oOu9xooziVS5akfKSd2my0uYlTpcscKZYGVLSRwJysq1FJJ0Am7VcFjvTiRZcivPCiANsITUNDATuzUbFsQUHkAO8y2sg0nUEvIoWstA67KmHQymwkyRRvUkdKI+oyTI9ScOWYyhWMMnPYdW02KqUDqbI3ZsspdIWXSjvsxmaFdNObaNiRgV03dNgQKTMSYd0Qt09dk00a0x3P94YO2fdmIxJeeFFA5aCVhkhCJqGcswpCr39yoHC6z4smERuPetG7FO+ZQe2wa656kR4PwNEAaEUbSV4sS+0Ij7Oq0bwQy8u4iirs86IZbcR7u7Jud+LK58XC5MP2PdpBP98gq4uO+CH0Zpp1m+Z9eXzYBIh0FXjhRQGZw67u5CSa6JI7zZIr9YBQWfLzkby5cAjUda6rsRkkBe9SvGeqeuHfNhGqTKKNwnB502gjesdNpjxF+jQop9moxnQEUTo8lpIRLruVdvpUO+wW//IddsM0ZTAbOYo2innWz8O+X16+nQ5E0Ubk/doavbq1Ghu5fCS1vaLjB7oqvPCigK3DrswJjEerSI+GSOVM2th5WgFb6I6v4XubOI7J1OfmTp8ivuTPZTSkwgtnJarnsCs2G/Hzuxnpee+fmdnIkK7y25TquKPDbpv6LKB9PADvYRnNRjLfGxNY+byALjsvztYyRCdgE1+OFArIeoxCpVUO5wXzsZFXXhyIQdCm0hqT73TwwosCSYdd4rdM80LREJk5GHOQgJ7IbETx52CU0J6ILBzHCAVskpyp34QDs5HRqdJcs5EatIuMWtPjzmxUPs2LqUyk7fBoX4RzqMqPeJZoXsobbZSOjpXJR6BxyLPZKPZ5Sd4DmDYYCYZymmIDoj4/xd9JAdJ2m4rOCi+8KMA2Ed1TpUkpWr+ZMapXoeYlNhuV+3gAsiybU6VdDOJih93Scx0amjQBUvOilz7iR5I+O72LyGE3Gxj7vKgGf0IAzcsmdcryJRqPcvp+OBd+jWQXWvuUl28nQ8wreY/UwsT3Y5ONnvRiI1zoniqtwUWXgBdeFGAHJG3Ni0Cal+UV7/PCpAufIxCmyRI2HvVRZ3RQvqjYSLDU4EtHmAgR+bwYDx7i9Pw2kd1HzIq282ijMB3INlNhs5Hmc1m0UTlewVm0kQXL7JjAE/jzhsi5WCCwkPe1o42ivDYMJX9Tbd9w8dTZ4YUXFVg1KOWwK/F5Ce2pglbGc+BLOr3xy6E1L2J6ptClYVNW7Hycnk9xnZaeawwdSTOOOE87bxWpMXrUSAebZH53Drtu6OjAlGcVa+QkkRe/CVWble0B4rLdq5Bq4iRgwzPb92wilsqNUMDScdit0XXY1TgDSQRadilekf2LGk+87sULLyokzUaa+Tgdg6KjcU/kjEvaX11u5GVqNjJxSiuH2Yh09jSlIbNl806V1nGYk9mos3SqLecOnMYbDCodHuN05dwjRQpF+TKLgkuNoxIpnEVJ2NQ7uwdJdWxSFxD/L4Iy9xMPdHfY1Tapy7R0IMYwwWLZa1688KJEYpM60/yC+3k0G+lORKJzTGTg2XBtofZ50dC8aGhC2LSU4kVnnxep2SiZP8t9XrKCcZS7cvCPV7j5MRvJy5eFKJfT90NmvrKjp8+0cJ+XHEsv8QKTr3rhmY2Ux1tobtfAbyvJ55SbgiBtV4UXXhRIeM9rdsY4ZJDfyvibtQnMRmy0EWFfdqmeNXbYNaDt0nGx3KdK81ai5g67THnq7NYoZySCuTCvt3TNk9lIVb5OiHI5XsHA5UsKm3pn+15eBE8ZQh51zEa6QomuACmLTCs+T445sujFrggvvCiQMBtpdka2EyegoXkR7RFBr+jdNWLtYYZZZenAJoJBSEuoedEbYHg0ZHnaLTepozU18vJZ+mlQ1mHNueallI7QvVRceNFMx52QHC4uVHC1fbydyYfue1URbcSYuIr3iN9E2hrNMS8WIOXp+P5RybJpzYs3G5HwwosCiWgjyWqaBE+qp+holC2yl9PhpEm+bKF9PEDpr53mxa7jBYLfJMw0L8y1TPNiGW1E+cgwTi58s5H+R5SVz59EsxntTOtEuXLlaV7KtHqn21jSZCCCbFXuchNJFWKHznTfOhANPBLKCc2Lu7VKZmBNXABf+wGYOC8nBUiViYhfdoka5fMip8lDZ5Zx6irNQF4QBAH++uJ76NujHh84cCBxn06n24afeGMTpo/pj+71tdzne/YlvUprmNANnqMoef39B5fHeQ2ll0LB/t1CPtdsaUV9bQ3e3boL08f0j/h6ZNkG3PbESnzxhHGYsf9+AIDX1rZY8Rli99726LdIPa+7OgJoYWJvewcef2OjMO1723YDUAuuLbv3Utdk+pbd+6hnPBZdRRu17NqrTuQIJM879tDv+PI72/Dq2m044aBBaG5qRBAEWLFhh4JekeCSNVuj71zpLeZVTVbW7t55f1eJiGOmOAj53LKzLfHsuVVbsGLDDry9uRX/cfxY9OtZHz3b1roXP3nkDWzZuRefnDocb29pBWAXbdQRBNjV1o4n39xU4im/4kuoUSU/Gzm2vLhmW/Q73mEX2NrahqXvtnBphvVAjlch1rfsxpsbd+CtjTvxxvrtiecbt++Jfgectk9WZUcQYM2WVtzy6Jv42JRhOGJ0fy6dHbv34qk3N+GoMfthw/Y9eHT5BnSvr0O/Ht1w5Oj++O3Tb2PqqH6YMrIf933yDC+8lHDvkvfw5TuXAAD+/p/H4tBhfbjpRvTrEf1u4wggIT7/20Xo070b/v6fx2rz0K02bp11tTVCrQo7Sah44eGg5t54fR3dgepr9RRxW1uLk+P5v34O+/Wsx+adbfjzF2Zg6qj+2LB9N+b8+jkAwONvbMLf//NYjOjfI4qu6VZbgx4CgU6GL92xBGdMHgbAjdmIxLz7X8dtT65UphvYqyH6zeNh4jUPUtfbGCFizZZWjOjfQ8ijiYZh/4E9I4GQxdw/Lknca+xmXuc6YCenZ97ajOlj98OaLa04/SdPAAAObO6FBy/9ABav2aqkt7e92I5/9UT8Pco1/w3qHX/ffj3iyX3N+62JtAOJtDJfk/97+m0AwLMrt7hhUoK29iIHi1dvpe4vXv0+/u2WhdH1LY++iVU3nBZdn/o/j+PdrUUh688vvCMtQ/QpyL73+d8uinjIm+zSnxDalr63DUePG8DVeGzesQef/tUz0f34bKMAM298DJt27AEP4fte9ueXo3uhkDT9u/OlvH39rpfw70eMKJVTokfUOGs2Ou57jwAAfvfMajx7xYkY1NQIADjyOw9H6V5YvRVn3/oMrjvjEFx17ytUeWMH9sRbG3cCAJZ9+2Q01GUzRmQFbzYq4f6X10a/X1j9fvQ7lID3H9gTnzh8OM47enT0rHdjN4rGn78wg7retmtvYgKTYVDvRhzY3AsAMLipUej0xltZDyAmVh381ycmUtf1tTU4aux+RjQAYHNplffq2qIgtGoTPdA/v2oLtrXG/E4d1Q+Dmhpx3oxRAIBzpo8U0v75Z6YKniSniT7duyV8cbpLJmxS+Lj9KbXgAgAfntCM8YN7lzhQi0j72uk0b2yIhcW00UbXfvQQzD5iBI4dNyDx7LlV7yfuHSYQxtNizICe1PWTb24GACwjBOPl64valg0tu4V0fnnuEQD4GslyGR9OPWwI+vXohqF9Gint69ubk8LLb+ZMI7hTe8pGGpgM0b9HcTwa3q87df/pt+SCUyi4sBjLfFsZ4nDxAI8uj7WYeXPYPfWwIdHvcHzghUe/30prr+pKC8uODnAFlwlDmgDE77uM0KyM7N8jkV4FnumO3meKTr+K00ZJ3L343cS9UHABgN1tZovfPMALLwqEbeS0w4bgB/8+iVqRjehPDxITh/dN5jdUA1w688BSuWb+LIP7mAkv5MoRAG74xGFCE1dahBN9j/pa1NcVm9y1ZxyKVTechu987DBhvlmHDObT49TpmZOHJnxxWAHj55+Zip6ld7RxdK4pFHDVRyYIeWAxdqB48OdrXvSxX68G/NcnJ+IrJx2oTHv+0aMTJklXqDOgG9bZkaP74SMT40lk/ODemDmhGQBwOEd9Xa7Ve21NAYuvOglPXX4ipVE6qLl3Iu2EoU3Rb51oo3JgSN/ieOSKizpNTSwg9oPLm+alsVstTj2sOK7I/BKTJnW5VvcTU4eX0iWfycbVicP5iwqe03SB87wrwwsvCnQwEoSsM/IemTYyymHRwOvfdIWTiGDKcJBx7bzHnfgLhcT+M4kBCEikMUIB0Fhka4FbvkUF6fgUZPltTWiTmkQTX4hKz3/KUOnS30pHgLjmw6TeRf2q0t+Oh2RUFql5CZg7YR76eZIm/VefFz54C1e/SR0NL7woEDaScIEpG8h4Dm6mjYyS8MOyNVa3phMUy2uW25eHVeCqDFGYcQ0jWLDJagoF4QpRBzWFgrvzYzgc2NSPjuIjy29rFCFFDMj0tucF7m/ZvXJC9Y7h8/YKzyg15NjhkJ4ORCHCWWn80kC0oR4g1sawYwuLeH4wXUTy0/PGTPp4AA8vvCjA+p3INBy8dmiqSg5JdASBUZilcacxSp0Org+n49VpcTVf/B0PSnS6AqE5sVHxE9lTr3z4xwOYQ0fjluW3Nml25GZ/lDpcZNe3KCMLqIpn212l4JwPg3oP2yHbrvMnusRjZXS2EfEsbKPJLTLk0kv43LStitLzN6mLLyptoswDvPCiAKu+k5qNeJoXw/KoQxc5TlvCfIblsBmyDGl0bjYSaF4S56sk7Nb6p8PyUCiobd/a4L6DeQ3pZMnUbGSQVmQ2ogZobhmV1rwonpf+6px3lSVM9jkyoZeq7BxKL6z2ldK8SEzOgFho0JkfZLywUO1x5GUXL7xogNZ+mPZF003kyI4lijbi5jPuNAXmOkuEqwhHZiPOzF9AUnWdHEcLRD1ZaF4K7la3onfIAlkKpmZmI4HmhQwHzaXmRdNsVGHpJQ5XdsOHSbXH4xajscih9ML2YSraKPrL0dpCPGrE84Mrs1FS80Lz4aUXL7wokNS8GIsvAPTtx2TIoYngUxUOu47KEGle2OcJAYOYNK00L0jnM0NC9Q660Gsb2cHK1EXa30C/Qx43NdPXvFRa9VL8407zov8tCoKOkcPPmWizJMsizUuYS1i3tmYjwX3xXlZhArNyVKhGYcgLLwqwu9ya+p+FjbBWs1WTTndBJPjo5DPjq5oddnmgnWnpcsk0PLOPbrelzEYp+zovu83ErVOnWQoEJt+UVIWT+UQmpKiMCjt9qt5R98ThrJHGJMqnZ1F2ChrlQmKcCNSjQeywK39uOsaJ0seBIvxx2nVLq7TcbQMvvCiQVvMSapJrdGu6EOYLlHZPXj5dsMmzHGNcn+/CnSQIk058onciSapVcjEc2z4/Ca7TcVaalww/rhOHXep3kmDF5z8VA2GbqPA+X641QEba3KgO8m82kjnth+yLzrRT7e5t/LaCDLyT7Mlr14JypQVvG3jhRQETvxNu/uiMCk2zUZSP73Euzte1zUYAafPn+6Sk1ZyQwk9qzUsniTYyQdwOClRbqPpoo9LfSk8AruvJyGGX6Hu2NMoFllfaYVe08JFrPKL3dGU2Ejx3dXK4qLxqghdeFEg78ZqaTKhoo/CeVj4zvpKTXoZmo6hnuClDOYAEIuGgwF1B6XJFCj9ZoCqjjQxok+2ZPrNFUUbFo43k5buO8rFFVhObVtmCOsih7JLgle+wK8ojiDZi/prykgAh6PMK8mYjL7woYbLLLTd/mmijaLTPYHVdTs2LwHPemp5iAAkElmnSXGHjoEY57Kbo7Sr+zXjSSZOhwGVAm4o2orQtesJBpaArXFV6kzrXkShmmhdB2ZX+eBywvPJDpQ3NRoXwr6EGXNC6RPOOi/FHVl41wQsvCogcp7TzlxpFrabnGrmDq5HDrqFnHJs8U4fdqA4d0RPcp/fIEZmNaJ5k9FjUFNw4zInGHZtvoDNYZuk0maAtGVQpzQvBt4q/Ss9/Kv5Cf7aKh0o71gCZtEeRs3BVOOwSz4THAxDjMg+2AR0iX0jSxEqld+yUHRfomF4Z4IUXBUz8TvgEin90o43IASgcC7Pwa2A7RZZjjJHjsRY90QBS/NsRCDQvhO7EfpO6uAzdPCxUG12Z8uQmkR3YdiSbv0n/L0rzomgXuTcbQT6xlQvxLreuHHYN0grMKpX+djywvJI8CzUv4XMRzeivG81LNPYLNOSum1qlN1i0gRdeFEj7TTsEErQIlOnDwORk7vOSLr8J3JuN+PfJAUYUzZNOtR6/QJrBw+U4oWc2yg4JxYvk7cj2TOXLueZFaTaKBNrMWdHiwxUbNodnVoXDLiMAUJoX0M/iPPJFj/PjAVRmI8eqEm826oQQqe+08xuYfooFkeWa+NsYSvwCiT4LxJoXR/QE97lHK5DP4eJ4ADkPOlDZzU2Qt1OlZfUaP2I1L4oyzNlyC00GKh5tFP5wxIZRvQv6VcW/HReM6ZfyeRGYjUp/hVpTZ7yFfJToJsbpbMxG3mG3E4K001vlN/SZocN9S/cy0bywZqMMfV7CMhzNojqaF+5zonwyjYlc6SKiQ7TKsfkGepqX8pmNZNVCa17ifKpmUeldd6vmeAAH/lg0PYO0pb+ibfXzBK1oI0O/Y2uHXUH6eN7hm/e9y4sXXiLQTlvkb7HJQ2cCC5Poal5Ie6xI68P35zBD4n3SDjIc+zEQCmGOVZw8egHxTkTdkaAddpMDlgr0/iTqXKwGKLani+hrMmKYp5wTSIdg5Vq8F2sSRT4vrva/cQnlxFX6K9O8lOMbiPxObE0CJgfNCkOlcyi9sIIWb+wX+rwo+i7vbWXDn7B2RPOO6BunHGMr7a9lAy+8KJA62ih0UjSONhLvsijLpws2eZbRRsa7DGvSYxFv084fsGsI4cVmkUxGG6VZZLuMNtLJU9aID0m9kE6IJN+qdpFl29SBqvQajTZVjjfQ4UMXplUu6hc5lF0SvJL9MRxz2feIowz5lRs+Nx3jRH2zQzDvuBh/eKhC2cULLyHIJkK2F5mzqU7HDNuEbqg06VOhUh2a8kLTUNM0I1go/eHRDVfcjsxGvAGkgHhVAr7mBfROLcblijQ3OunD65A/PnfZoJyrX6mZlYg2IqE0IVV4AlQJT4VoQhG3ifIIYPwJ1qU5Un0/fdlZg9TQAnR9RWajxH41VBYxbc77yj690GwkcBQUaX7T9nEvvHRCpHU2tT8ewJ8qLSbIv02OSaJooxrNQYhP382p0uU2G5UTMqEu9n3iC3UiVPoddc1GUvNAWc1GLmjZjSemviKVANuHKZ4D5m+Up8C7HT+3jTYS3BctAnTamg18tFEnRECOuCny62anNS+xj4BuPl0kO0V2o4x0NZ6CHgve0QrUczKNTcEFNxOEin8jliocbcRCGm0ULQQKRu2t0vOfrnDFHkpIpSnDW7ic2Ey5FUXBVPrb8cDySvu/8X22YnOzXGtqXm/8+yJ/x1jLZ1iQAl7z0gnh6ngAfbUx0bFcayzIUhKdwn0ZIdKGm4vosSBXVHyH3QJ3gDf7MuH3se/tLp3jtATbMk4hsjcjVeG05kXPLFM5qMovPpceD1AWzYu7QmxJVUO0UQi5wy6dViUYRu9p/MICs5HgaXjtOiy/CmUXL7yoIHKc0kXk86KZPzJrEMOAnlOmGX+sC062wou+47EWPYXTXCBQvdQUQNiuk3ZuFWoKBeL72IOX19apNm8Ouzr7vBRA86Tcfr/CE6AufzLNSzneoYbTtm1hKgiJjwfIn/SSOB6A4Fnk86J6j8hh1/B1ReljdwP6vm1YvqpJ+GijToi0/hqm0UaRWrDDTLo2NhtJnCbTgNcJ4mMO3EDUb0mTDk/AIY0VNmrXoq8Gf5A2QdDBo21XO1r+UGWcP2RtltxtmnxftV6jshOgttlIqngph9nInUnB1vxR6V2GdcDySo5ZomgjlaN++cxGNJ9xennFqz5LNXw3Fl54KUHlZmg79MSaG730ZDITc0vaCcqdVoR3L9S8ZCcgAaTZKOB2Rkr4sIk2Ih1205iNuIKVHfJmNpKBXE2SHOX/VGkFf5HQIPF5KYvZqPjXhfOlrQ9d0myUj7ZHguWVbzbim7+U+7yYOjoLzUb8eUe0+FJ9cfV4VX3SixdeShB92/SRMuGArat5CcsNKDW7Ml/KCSr1EBNtUsd75qgMmlwSpOZF8EFr4pHLGFSotHn2CKIN9KyQM82LVgh59D/iOsdwo3kpH9w47BpOwoJ+lcdvy/Iq2POSzQVA9o0LxP859EQLLoXmRRQqndS8iPhy8zyP8MJLBP7Xi9uQpc+LseYl1AyY+Yqk17ykIyCyFZPPsg+VJuqO97xApzFFgSwjjdmIS9vSbJSz6UFULeyO0WbHA7jhzRZKs5aGr0k5NBAuBGuWlnZ6Qb+q9LfjgY045JpgRGYj0R5NBfovC9PtEUTzjugEc5W2Tf28+mAlvNx8880YPXo0GhsbMX36dDz77LPCtLfeeiuOO+449OvXD/369cPMmTOl6SsFseZFX4Dg5i/91fd5ifmJ8pbBKTNt/iCWXoTPXDnviR12w/L4m9TVFApU/ZqCPB4gjWqeN8nZVo3Odyun06RMg0mqwkm+VRN7Hp0+Seg4UZbjFdIcOiqipQuRAJfHb6cSNnk+c6r9ocL3VJ1VlORFkF6w6A2v21m/Oa95UePOO+/E3LlzcfXVV+OFF17ApEmTMGvWLGzYsIGbfsGCBTjrrLPwyCOPYOHChRgxYgROOukkvPvuu6mZdwmRvZp0MrRBSFY32ohUC5oJTinNRinHGJGjG/nMFTo4Dq8A7UzL9Ssh3tGGJ9JslMbBTeSPY4O87fMi7keEH1KB5kmp2XDCWXYI+ZOFSpfjHXQ0QNq0jMvmm1VyKLskHJvZ6uoIgsQYo9ykjvnLwvQ0atHRMCJBWTUeqZpEpU9Et4Gx8HLjjTfioosuwpw5czBhwgTccsst6NGjB2677TZu+t/97nf44he/iMmTJ2P8+PH45S9/iY6ODsyfPz818y4hVHeX/tr2wXASTXWqtE6+1INESrNROBBIzUauNC98UGpznoCAOMrF2myUQjcvqyN7s5GbNK4g60eiTerUZqMczoAEdCLQymI2SmES5RCzSp4wG7ngxTFY7SvbH3lm59hPxrXZSF5DQodeY7ORHFUou6DOJHFbWxsWLVqEyy+/PLpXU1ODmTNnYuHChVo0WltbsXfvXvTv31+YZs+ePdizZ0903dLSYsKmFV56Z1v0+6p7X8GEIU345C3xO9mOPeRhdDoI023cvgf/WLpOO3PaQSLt2PrH59fgs8eOwR3PraHuX/O3V6Pfa7a0pirjT8+vwb8dMUIZbbRy00607N6bfF6gTUvv72zDlOsf0i6f3OSurb0D3//nMhx3wAD85JEV2LyjTZn/a3e9hBe+9WGnBmY9f6jyTSFPrtgEIPmKb2/eiQdfLbbn3fvaKb5VA2ceJ0ASIX+3P7VKnKYMLxGWsWVnGz76kyfQtq8DBzT3xtC+jYm0oy+7D8cdMAC/Pv9ILq3tu/dZlf1U6fsnHuQIoZbhtidX4uAhvfHd+1+nnh9w5T8SeUTCWfS8lGBvezLF4tVb8fGfPcnNt3MPXc972zvQEQT4738uAwDs2dfOLeezv3mOun/B7c9jxv77Ye6HD+SW89pa+Rx6/q+fxW3nH4lDh/WRpssTjDQvmzZtQnt7O5qbm6n7zc3NWLdunRaNb3zjGxg6dChmzpwpTDNv3jz06dMn+jdixAgTNq0war8e1DUpuAB8e/bUUWIBLMT7O4uTmmm0EYme9bXU9UcnDU2k2a9ngxZ9YbkGaWcePChx772tuwAA9720Vphvxx6zAREA6gij79fuegmAeADp3dgt+n3jQ8sTz4uaE0Q0vvKnF4146dVQhz7d4zJ+8sgK/OcfFuPxNzbhVc7g8IEDB+Jrsw6KrreU2gKP/1172zl31dDR2Azpk5y8skKP+uJ6iBUwP3v781i8eiuAYhtZt2139IxcOBwytClBs9Lz36xDBlPXvRroNd/bm3cqaVxwzBinPPGwX8/66PdL72zD6+u2428vvoefP/oWN/3jb2zCvUveMyrjY4cPBwAc1Nybut/aVmy/fXt0o+7nT3QB/rk0nqvCMUWGs6aNJMxiooVT8fmit9/nPl/6Ll94+NfrG3DejFHR9cvvbsNvn14dXd/DfJ+wL+zeS9u12to78Ojyjbj2b69I3kSMDdv34Dv3vWaVt1Ioa7TRDTfcgDvuuAN33303GhvFA+rll1+Obdu2Rf/WrFkjTOsKQ/t2lz4fPzgeVBd9cyYevPR4jBvUK5Hulk9Ppa73ljyramqAey4+Jrp//RmHcMvhCTnHHTCQuv7YlGHUiun8o0ejDzNo6OCqj0yQlivCTZ+akrjXrTabpvTjs5JlhePHmAE9qfuDiUn63a27wYKKcgmKGhoSMw9uxtJrZ+HCY/kTzdC+jejJTFwbtu9JpPu3qcPxp8/PwJSR/fCFD+wv5J/EgF71yZsaKEiq/YpTx+POzx2FmQc3ixM5wHNXzoy+Rfge7CuuZrRuU0b2i37vIxwMTj10SIJ+pc1GR48bQF0/+Y0PUdfTxtCLmGPHDUgI+Bd/cFw2zBHo39O8Db3f2mbU9k6fOAR/veQY/OWLR1P3Jw4vrtjZcSCPDrvbdiW1sjJcd8Yh2vu82OCq0+O5YF97gE07kmNKCFV9rtrcas3LmvfTacbLDaMZZ8CAAaitrcX69eup++vXr8fgwYMFuYr4/ve/jxtuuAEPPvggJk6cKE3b0NCApqYm6l/WUDm5kQ1iv14NOJBZecTP6IEgcrxCAWMHxpNtnx78AYPX7hIe5zUFHEMMqPtzhCgdkJO9SYPv1VCHemaQysrhq6FbsomG34oddGlTBN9hV7RPAgAcd8AA9Gqow/EHDkw8A+LVVX2dvNt8+qhROHJ0/1KZBRwxqh/1nFf2oN522hHZZ5s6qj+mj91PO9LNFgN7N+BLJx4AIH43VX+im0/MX01NAZOGx6rrHM59iYVCYzdaM3rsAQMwaXhf6l7W3wAoVzh2AROH900I8bUCzUQev59pPXWrrVE77JZodmfagg5qa+K5QTWO6nCeR4ExCxgJL/X19Zg6dSrlbBs6386YMUOY73vf+x6uv/56PPDAAzjiiCPsuc0QSru7rs8Kcx2GtBX3GNHIz0nE62wu2meB+m3poVdCVv5ePL7EeyDE4Jn5CkQa2UZxwrotUH+ESEYI0Ne8usoi2qicY1jCCdKgQYgiKoB8mh1YsDyS5slqgJN1h0AzkcdqsOFJqXlh0hnTh5x+zIe6gGo8p8gGRg67ADB37lycd955OOKIIzBt2jTcdNNN2LlzJ+bMmQMAOPfcczFs2DDMmzcPAPBf//VfuOqqq/D73/8eo0ePjnxjevXqhV697DQGWUDtNGjns0JK0noSP0dQ0UplDipcNZ3skp23Oocv8e6T8Q1+OHKseuEKENFffmUohRtBfvba5T4vsmyVmDjiCA59JCZ/ql3mcfpjwPBYbGZVwHcJLrSm1bVJnUWe0l/lJnV2LBFRkOk1L11DdLEQXmbPno2NGzfiqquuwrp16zB58mQ88MADkRPv6tWrUVMTK3R+9rOfoa2tDZ/85CcpOldffTWuueaadNw7hLLRaLdK/kRFRqqYlqOrjTGHPY2ENiEj6YXHoercDxE/BShO3o02mpLzojzrRsYYBFof21BpSbZyTqDs4JtK8yL4XS0ofsvqmUKcKF4E/SpvO0AXYc6TWvMSjh2W/Tj8ofoYGuS7iOLFXHgBgEsuuQSXXHIJ99mCBQuo61WrVtkUUXY4Mxsx6SKzkSYNvpZFoY2xbK3pNC+MkGbFgUY5HMa4500F9DXXbESY7or7jrADLf1XxEtaLRWfthnNmLbEbGRH0pKPImR72ZAgqz6hqSLNRnmc+1hw/Dyqgu8S3JyFVKIlepAjWGleor18stK8FP+S+yFx0ynopDowtsqEHn+2UQmqHQp1naDYdKFKtqagu80/R1DhfCUXgyNZlqmTF+t/mFXD5/k5xnVaYNLG17zdTovHA4gHIVUd1GgOUCwdmSkxTuNe81JOxz12a3qTHYilmpdqkgJKKBQKVeU06UJrGjoks6TyWA82HGlHG1m+blhPKhOeqj6rTP5IBS+8REhva+SlI81GWvl5JiJuuhRqEw5dY20CkyE7s5FEsyCzLygc64Ig+Q6qASjkRTWAsI/Z9Pxzl6QktcvSfeYa8cpRL9qI5E0m7OVv6uOA5R9VwncJDv11hdrMPMFGoFIfD6A3NqgQBOn6dJphOIdyphReeCkhM7NRFCqtazbiaF4yalX0JGFWhqaskBq8Vye3mRel5WleSHW+zGFXyYsioU20kS3y4lPAmo1S0ao2sxGDajMbuWiQon6Vx3qwMxsV/6o0L9bmX0kgAZVO0d+7SqQR4IWXCOpPrqk5YdKRxwPoTDS6mhcXSKW8KZPZiMdW5LCbMDfEN0SmGdk5NNoCqvI5uxJXa6nS2spNn7kGO3m5c9jN4eynQFHzUj18u9mjid+vcim8pMijOmDRuh+X/ppoLHnoOqKLF14ipG00onRxYy+kkMrt8inpEl0tpeyidNC0hkTzkkhKpOWdPE2q820OR4xXV2ZmIx3NS+ooBe6zcs4c4eRVMhulaA8OLKIVRVFIrjQX+nAabcRQy6MQZ9PXVFliZ37LfkwI/2lkyS6kePHCSwjVN7c9m6ijw9Bhl+P8kJXTGz1JmJXB8pmdw26Sr7AsmcMub4VUQ0wqQcCxzyuqIKSv8k9RPXfp8yJrGzVl7N01xOALpLS9ExNeHh0+VagpZGfqzQIu+m7kcMosGvJYDTY8xQ7p/MrSdeZX0VdNREqH3S4kvXjhpQRVdIRuo5SbjdT0yrpWTuFbkNC8lNFsFB25IDE38M1G8ffpCJK6AfXx9HrpWK6TDrvliTYq56o3PrgO1F87WsTvFDxVDIU86hvEcKE1FY5nOZRerHxeSn+FDrsF+q8x/VK+jiBI57BrV3xVwgsvJWRlNgr3GykwZiNVJ7Ap2xQ6wpQwLzshZ9RtuPu8hM8SaePf7SKzEfkNWPu8Ji/qdPJrG2dhFU86fGSJqCjNs41kqKly6YVtZ3mHGyfrkFb+o42sREuJr1xItZgsnfk3beBIF1K8eOFFF7bHAwSElkCnYfM3pMuf2ahsmhceW5E2q8Ckja/5O+jS+5Ek7PMqu7ZhOtF1uQaY8mrxin8js5EDWkA+Jz8VWC1r3uFmk7pSv2Lv57Ai0mlestmkLhKOlHwozEZdSPfihZcS3B3MKDYbaeUvq+aFMBuZ5tXQJrgAX3YJhM9CcM1GhPYrQGAcGRE/V5iXFEIV11k4xTcW5a1ItJEL6YWim8PZT4FiO6sevp2YjdjvH97PoRhnw1Fs1pHTtDYblf6mjjbqOrKLF15CuDrbiHW8jPZ5sXT4LdLMZgAgeTUto2yb1EkcdmV1yjsegHzfosMu+1xPKDF12CUveeXqlC0vj5+3omcbpYo2ivm2dWSuJIrO+ZXmQh9OzUbMd89jPdj0NXYHadFzW2GNdXgXQdWnvfDSBcELrSVhK3xEZiM2nSg/12yUESizkXVWAOkcNKXlcPjS0Wbx93GJV8QdnGijNDxRz9l9XpgoKFEklC3Ebal8CMsK+1Eqh13ydxVpMEIUqszpxc0uL3G/ou7nsRpSmI1EtZXeYTcUjhSLaAUdbzbqgnBxFDkvZTiYpzoeoAxmI+O8ZRqU3JqNaPWsabRRTEeloRFfi/ZxyMZsVAnNSxGutinP49ynQiGXxhIxXGhNRWajPH7BVGYjwSI3OlXajiXvsGsBL7yUUI7jAajyRPm5NLMZAGiHXcO8HE6zMB1pnyrNQOd4ANNoI5KOCVizkWuIpspKaF5cbFJHaqFyuXJXoVBdfLvcpI6llsd6sNukrpiHN64Un9vTJvOrHXbl6EKyixdeQqT18o7T0RDtSSLMX87VcopyecmzmZg55UTPxDzzzBYFFKjNoEyjjWQ8yejQmpeko3BqCDUvjsuRsZAwl6agJbmqBhQ1fNXDt9NoI8sFQTmRhifVUQr2Drtyn5qYvsrnpeuIL154CaHc2VCPDOu7EO+wq0egnA5u5C65puVyd75Ny5BmOWEPl+0g28GRXgo1hIaAI0To76IsT5c4JZm0mHOEJpOy+eXp8ZElWIdGV6HSeXT4VKGmUKhKvtNA5HCaxx2S0zjs8sYV8rm9z0vxr0pjqWpXWfke5hFeeClBeTiZpdkoci7VJFfWXVEdl+vmgDcaUoddqeZF4PMS2q4DjnNhCp5kzynNC6dcIN0knYdVfshBWO/pVoDVbTYizZN5h6suG/erajAb2ecRhkqHZiPLvqiiH6XLQV/PC7zwUoI7sxGjeQkE0ouYQNmQyuelTGYjHgKNOuWajYphICUagK193jTaiFzpFTU+PH8c+w8vdti1JmnBRPGPe4fd6husC4Xq4dtddIrAbFQd1aAEK5wnnhfov+b0w/pzs4juCvDCSwmubIVJzUvosKtrknDChiYKnF+aOXnCSwaGI345pWemtAh6fN8TOwE18VyiZiuajfi82UKoxSur/xQ9+KY7HoCgW4WDdQGFqplkXGtekscDVElFKCCOpio9TxttpLtwsqTfGeGFlxKyUhrEodJ65ZV1sUzbjczycqON0vFjWo6Nk3ENMQglQ6X16UifS66zCZXmZ65EW4o0L2lopRCq84BC9cguznwkwvetgkhpK4Rtkrf5JZBeyFYJR67K6UzwwksJqkajq1XQDZUW57donbabrVG/zQWBciAZxRLwNS8aVVBAvANHAI59XpOW8tUTPi+E2SgI1AUYQqx5cVqMHg+hw66qPwX83wBrzqyC0dqxGbCccKUtLbDSa3jfCXW3sBkuw9cThkqn4KeYPxyX5NGIWWqyqi1QyQsvJbgyG7Ge7CHdPEYbpdmGnfc+WTjsJuuTrFMzWtQ+L0E5o41i8ByFdWjK+dHjI0uEkWthG0jTFtL4YuUBNYXqMZa46rJhX2S/ex6jjWyg2gE3rbAaOewqdnqXRVh2NfiqKMGZw27C54V/X7hathn2bDdGokgYal449zIxG3HMbVyzkQb7tPDCsc+HNFRmIVOzEWM34m2ylyraKA9mo9Jf3SYgE1Aos1E1zH2ssFqoEr4doqucKq2KNrIFuUO1jFaWYnEev5UMXngpwZnjmiDayJU/RVYwLpaTIQutI1sMeSqzKc+U2Yh7PIAdT4nnDCFRtFEasx1dnuiBNUlrHqJ9XtxESlelw2c18ew6UKEaTpW2gSgUPHqeln7pb9pTpbsSvPBSgjvbL30dO3jlu9UZh0pz7mVzPABTBogB0sJsRIX0Wg60Ki1VQvNC/CYdhUk6qRx2hffLr3txcap0tR8PUE08u+6ytrtW5x3ha4gddt2YjarM7aSiqKs0A5XEmi2t2LW3HT0b6tC6p90JTbYJb23dW7yfe82LodmI5/OisNfagS5nx+592L57X+mJuakrnBi3796H7Xv2yYrS5IjzXCK9bNu1F1tb20yKU/MjMhtVQPPy3tbdWLOlFe+8v8ueluB3taCaeF6+YYcTOmLNS+dA2MeWrdvOf56Wfunv9t375A67nUUadIAuLbz8vzsWY/HqrVpp9YUPOuHL724DkPRp6FbLJ2jj4NZQa6dAo1a4hiR4PhqTrnvQig+TcqZc/xD3WWNdrZJWoVDA+zuLgsONDy3nlFUk2E1Rn4P7NOINyaDPtoGe9XE3O+H7C6Lf+4hVXPd6Nf8ibCm9E4tKHA/Q3hHguO89okxfXxfX8ZA+jdSzsM8ARWEoD+jVUIcdrLBbQvdu9t+u0vjbi+85oRN+/7Z2egWTx8m2d6P5tBeONRu27xE8L5Rod7PiKRwKrv/7q/j0USOj+43d6LFoX3smK8SqRJc2G+l2qw+NH4QBvRr0aAqIhlqCL5ywP44a2x8nHtzMTaeaOEl8eeYBOHJ0P3x08lDtPCQOGtwb08b0x2kTh6B3g1mHtjFJXH/mocZ5ZINfoQB887SDMWlEX1xw3Bhumt4NdZg8oi/+/YjhqK0p4IkVm7jpxg/ujckj+gIApo7shw8cOBAfOHAgN+3XZh2k4Jm+/vLMA6TpAeCyU8Yr05iiXw+7gdQGJq3hZ+ccjlMPGxJdX37qwdTzlZt2Rr/ZybBS+O2F0zF+cG/89oLpiWefmDqMut6PGSuOGts/U95IzBi7nxM6xwvavghCzUv+ZBf86FNTtNPedv4RxR+SFzlgUC8M69cdAPDD2ZONePn+v00CAEow3tceV+LdXzyGSr98PV/zw0LU9794wv7ChTO7iMg7urTmhTcxnn/0aNz+1Kro+pIPjsNXFZMVRVNYVvHvN052N0l9eeaB+PLMA63z19fV4I//McMqr2pQqinEq4lVN5xmVQYgnxQLKODC48biwuPGRvfOmjYSf3h2dXTdvb4W91x8DC97hAuOHYNvfWRCdF1TU8BvPjsNAHDpnUtw9+J3qfSHDu1jxDM7mZFIUzcqlHWHXUFR584Yhf9d+DZ17+AhTWioq8303V1j8oi+eODLx3OfDerdiNH79cCqza0AgP161eOd91uj578878iy8AgAf/jcURh92X3cZ9edcQiuuvcVYV7y+blHjTIqV7SYyaHsgqF9uyfuvXTNSfjSHxbjkWUbAST7peg9fn/RdBy9/4DoetygXtHv848ejWs+egjOvvVpPPXmZm7+icPFY8lpE4fg4CFN1L1jxw3APUtibVldTYHS4Ib47scOw1f+9CJa22h3iK+fPB4fGj8In7xlYSJPtTlXe80Le4+5ab6XSPV04izhymQhDRvkPEuE3SquAYuoJUUGXhvo7KcMm0xeeVyNpwXlfM0+Ky8rQigdzVM4Sgs1zlXysVXjlUqjbpO3mD+JUHulM4aK6908TxbHu2SJLi288BpH4p6D/U+KZKqjE+tCPRA6KsfCKVeWn/fNzQdqxbtb5Kl2mExe1bbC0wHlZMzZ9yUPUAnQtWmEF9H9nLy7CkonfJFwrvF+svbOy2+yK7uYtlxnzYPfYbeawPmGtSmXyCJpuVo6sS5U1eRqgjKtN7b+WT555Gy0RLIsXAHJuITqgskKsLP1BYB+J7bN5WWX2VoFH/SBmIaLBkH6atE46pjB+fdTal64UZv6e4OJ0sjqXfSsymSXri28uJrIlETR+VabympypXlJqb7WWgVb8Cpd13SRCZuEqH270HRVA2izUT5fsEYhSZDP3ZlS81kXLIxPilfcp9NINC+cex0mmhcLc53oWRbHu2SJri28cL5h2pVCmkZeTVB2dlflODLbxc/dmDHM+epkDYCBSXV0RhMabTZinuXkdZV+HeRvZ+ZyIzIVg9KPLYVDsnyhw9G88I4/cciX6FmVyS5dXHjhfMa0mhcbC2Q1Qu206qgc0/QqTYsjrYjXvNAQOzTq3at2yJ0y8/HGqoUZte+TIe1qD1Sw1SSnMe2IyJoeKWNcpjcbVT94J3Tq+EjIkIfdTssB1euUI9rIJr+rydR0sups35+FiUNjZ6wL2WGSeXlfk4gadw67OXl5Bew1yTraEckzzsPYbGRfd1bCdJWpXrq08MKfZOh7pp8zjWNXNcEm4sYGpvXGpteJNrJz2BXn4bWBvKy+s4JJu+9sfQGgJ4uk03g+3lfl8yJ7ByXtTu+wa/9+srrkPWs3cNgVQbW5Jw/VJbp0deElg1WhcJKqkk6sC7XZyJHmxTS9hTnLvdmo8pqXvJTHD5XufJDtkZKX9zWJEDTmWTjs5eXt5VBajQzat25eESKfF8vyRHlV/HiH3SpH2s4mtv1XRyfWhaWJ2H1BhsnLYzZyU0YalL+1GZhLO1dXAEC/EtvXc6J4MYuoMe13KXxC8gDbfavSihI8uoHE5yXQFDDkEU78Z1Umu3Rt4aWcK+Rq6cS6UK4AHL2v+WnXquduVC+mG0+V2/Zf/vIM0nZC6UXmL5IXv48sv1E+3tAe6kVPRv4nsmijNGVa8OOFlypCFovCdBJ69aBcmhdjx0ELXxznmpc8mI3KW5xRlF1O5nKnoISXyrEhhYovKtrIUb+rlm+dZfSkVJDg3AvNN7yAEu0ypeMT/36VyS5dW3jhOlZm5PNSLZ1YF3nweeGtFNj0ifM6DNkSqWmNfXEM06dF+X1e9Nt9J+sKAJh+X8jnKtZkgnbVvqtFy1YoFKwmb508OoIEOc60RwctqutOdB5RAQVhGxSbjXLYaCXo0sILf4WcrrP5aKMiXEUZmNabmi83jLnmyzXKPWl09Wgj8v3z+n5qrWT8XBWZxEIYjdNJZpg039Q02sjFPi9WxwNUl+zSxYUX3r20mhfRCjQd2dxBaTZypXkxVH8mIz0K0ufqMtzYAfMS/ZNZeUKNY+VNaGUBaXJBPt9R3Wf108ry0mXmsCIEsPET0Xk7Hed+sp90dIhpJzbhlES3mjpR+1Olqwh8lXa6zibMncfRLAXK5K/r3HHQHV/Zpk+LvAhLfB+jztUXWOTFQZeFiT+Yq1fIaVUYI53zrIb0QkCmedGONrLg12teqgruV4Vdx2FXMRBWSEoomy+ONxvZI8esuUBeX89E82L6Fp193EvVfaWyS/Jh4CLayCJrlckuXVt44e+Emg7V7nWvi/IJCYbpFV/QlS+OKV/l3mk0N5oXQzNdZ0Be38+kz7rqd3mtC1NkJLtw66c9jDZKUahNVu+wW0XgNZysnO3y6sRnC5MTarMsJ5lelcINZ+bfs7zfv9ztTbx9evJ+Z+sLLPJqNjLps676XV7rwhRp3sP+eIAUZVpIPtUlunR14SUDs5G4rM6FLPdFoOgYZyiPOcuVQ2NWyIuPTRbazbwjt/O1iebFlHQnD1RItc+LmcuLVAPi4ngAEapM8dLFhZcy9qzcDmgZwZXPhbn6Ot1z7XIc8+UcZReWRGaD8i0Q8oK8vp5J33DVvjuN5iWjvLzqiXbYzUhgEsGbjaoIfHt8Np2ts3TiELZngRiX48hxUPe5QUlmqTu55sUEuXYmdoC89nWTPuuq3+WzJsyR5puanjMURRtxnXl1BQxvNurU4JqNKsBHZ0TlNBwqu35lNELl9vPI6wQKeM1LpaDiqysfD6BCVpoX3sPQ5yWVw66V5sW+vEqgawsvXIfdbMrq7E6KLCoVbaT6fu52/jVLX+6vX+7oJhF47b6zd4W89nUlX6TmxeIVyhkAUW6kO2dI5rCbvOdmh10bzUt1SS9dXHjhDaxZmY0yIZtb5Nds5EioMuara2pe+A67+eAtK+Sk6hMw2VjS5hvl9LWdoCKnSqeYn2y4DXf2rRZ0beGFdy+jHtiZOzYPldqhs1yTdl4nqBB5Ya8r7vOSVygddlOYjdj8aejkEmlMOIbPYp+XFGV2lnqXoGsLL9xVYfnK8lDDdbV1mVDpnLS3ruhXlpe6T8BE82IjvPDu5bYyzJCVIMF7FugfKi2ma3U8QBcwG918880YPXo0GhsbMX36dDz77LPS9H/6058wfvx4NDY24rDDDsP9999vxaxrcD9vVmajTj9kZwPzbfjTPdcvJ9/RRnkREcoZ0ZcX5LWvmxzpYWU2KuNisNxIFW0kqQXes2iTOn88gBTGwsudd96JuXPn4uqrr8YLL7yASZMmYdasWdiwYQM3/VNPPYWzzjoLF1xwARYvXowzzzwTZ555JpYuXZqa+bTg7/6ZTVmdfLzODKbfQ+Wo5sqBMP/RRmUtTgjeoG/yTfPyHibIi7M0C7Uze4H4bU6f/61zWhmGSPNNZc6+vOrx0UZ6MBZebrzxRlx00UWYM2cOJkyYgFtuuQU9evTAbbfdxk3/ox/9CCeffDK+9rWv4eCDD8b111+Pww8/HD/5yU9SM58aZXQm7OyrzaxgrOFI+Vy7HFNfHEflVhvSmhKqsd7y2tezPlW6nD6E5Ua6eUGieeGajdJHG9nw21Fl0ouR8NLW1oZFixZh5syZMYGaGsycORMLFy7k5lm4cCGVHgBmzZolTA8Ae/bsQUtLC/UvC/jjAToffLRRvpD2taux3vLKsbIqC8ILa/p5rQtTZLXbLW8c2bprr/CZizJF2LB9D9ZsabUus9wwEl42bdqE9vZ2NDc3U/ebm5uxbt06bp5169YZpQeAefPmoU+fPtG/ESNGmLCpjd6NdYl74wb1kl7rgKfu45UlQi1BYHi/7sbllwP79ayXPj9xfPGb96ivzYyHUfv1TNzr3diNuj5ocG/qeubBgxJ5Bjc1Css4fGRf7n3R9+zVwL/PSz96vx7Cck0wYUgTAKCJKGPG2P2c0NZFzwb+dx4/uMmY1qThfaLfZ04eZs1TOdHcuyH6XSgAYwYk22a58JGJQ7j3ezfWoU/3btxnANBE9B2T8SrOk6TdmGH/d40jx/QHAIzonxxzRfUxkPjuLCaW2rGsLsOx/rBhcZtvbWsX5iP7BgBMGtEnkQYojkPHHzCQunfi+OLY17dHPHaP7E+PQRt37BHymjeYt9Ay4PLLL8fcuXOj65aWlkwEmC+esD/qagqY//oGDOzdgGPHDcCRo/vjf86agv/3h8U4+ZDBOPXQwcZ0//T5GXj6rS24e/G7WN+yG5d8cBw+MnGodv4FXz0B/1i6FjWFAk6fpJ+vnPjqrINQALBpZxu+PusgXHXvUozo3wNrt+7GOUeNxKxDBmPcoF444aCBSloq/P6i6XjwlfV47I2N6N1Qh0072jB9bH98ZsaoRNqPThqKnXv24bE3NqG+tgbXfPQQ6vl/nngAVmzYgfe27say9dtxxuShOHOKeII8a9pI1NXWYFppYAvxX5+YiAeWrsPDr61H9/paHDK0CU2N3fDhCc1cOjd8fCL+sXQtHli6Dm9s2IHxg3vjzs/NsKiNJH5y9hQ88Mo6fGzKMPzq8ZVYvmEHvvmRg53Q1kXvxm645vQJuOZvr0b3Pn3USMzYfz9875MT8c17luKUQwdj9pHqfvzbC6fjpB8+ht6NdfhWmd/DFt/6yARMGNqEI0f3R6FQwJSR/fCjT01OTA7lwFWnT8Cg3o34x9K1WLttN/p074YrTh2Pg5p7438/Ow3zX1uP1rZ23Pn8GmzfvQ+9Gurwh4uOwiFDm/BfnzgMPerr0CwR6EW4+ezD8ejyDagpFNARBJg0vC8lEOUJz105E0d+52EAwN1fPBoAcP7Ro9FYV4tjxg1IpD9sWB9cOvNA/PDh5RjWtzs+e+wYDO/XHUP7JgWdBy89Hi+8/X4keF947FgAwH0vrcWJ4wdh9pEj8eraFjQ3NUTCy5dOPAC72tqxeeceHDS4N3o3dsOnpo1M0P7UtJF4c+NOLFu3HTP23w+fOHw4tu3aiyvveRn9e9ajta0d50wfiRH9e+DaMw7BxBF9sHLjTmzcsQff+dhhAIABvRpw5akH4+m3NuOmT03G/S+vxdubW1EowOq7VwqFwCA+qq2tDT169MBdd92FM888M7p/3nnnYevWrbj33nsTeUaOHIm5c+fiy1/+cnTv6quvxj333IMXX3xRq9yWlhb06dMH27ZtQ1OT+UrOw8PDw8PDo/zIav42MhvV19dj6tSpmD9/fnSvo6MD8+fPx4wZ/FXkjBkzqPQA8NBDDwnTe3h4eHh4eHjIYGw2mjt3Ls477zwcccQRmDZtGm666Sbs3LkTc+bMAQCce+65GDZsGObNmwcA+NKXvoQPfOAD+MEPfoDTTjsNd9xxB55//nn84he/cPsmHh4eHh4eHl0CxsLL7NmzsXHjRlx11VVYt24dJk+ejAceeCByyl29ejVqiMD2o48+Gr///e/xzW9+E1dccQUOOOAA3HPPPTj00EPdvYWHh4eHh4dHl4GRz0ul4H1ePDw8PDw8qg+58Hnx8PDw8PDw8Kg0vPDi4eHh4eHhUVXwwouHh4eHh4dHVcELLx4eHh4eHh5VBS+8eHh4eHh4eFQVvPDi4eHh4eHhUVXwwouHh4eHh4dHVcELLx4eHh4eHh5VBS+8eHh4eHh4eFQVjI8HqATCTYBbWloqzImHh4eHh4eHLsJ52/Vm/lUhvGzfvh0AMGLEiApz4uHh4eHh4WGK7du3o0+fPs7oVcXZRh0dHXjvvffQu3dvFAoFZ3RbWlowYsQIrFmzxp+ZZABfb3bw9WYHX2928PVmB19vdhDVWxAE2L59O4YOHUod2pwWVaF5qampwfDhwzOj39TU5BupBXy92cHXmx18vdnB15sdfL3ZgVdvLjUuIbzDroeHh4eHh0dVwQsvHh4eHh4eHlWFLi28NDQ04Oqrr0ZDQ0OlWakq+Hqzg683O/h6s4OvNzv4erNDueutKhx2PTw8PDw8PDxCdGnNi4eHh4eHh0f1wQsvHh4eHh4eHlUFL7x4eHh4eHh4VBW88OLh4eHh4eFRVejSwsvNN9+M0aNHo7GxEdOnT8ezzz5baZYqhmuuuQaFQoH6N378+Oj57t27cfHFF2O//fZDr1698IlPfALr16+naKxevRqnnXYaevTogUGDBuFrX/sa9u3bV+5XyRSPPfYYTj/9dAwdOhSFQgH33HMP9TwIAlx11VUYMmQIunfvjpkzZ+KNN96g0mzZsgXnnHMOmpqa0LdvX1xwwQXYsWMHleall17Ccccdh8bGRowYMQLf+973sn61TKGqt/PPPz/R/k4++WQqTVest3nz5uHII49E7969MWjQIJx55plYtmwZlcZV31ywYAEOP/xwNDQ0YNy4cbj99tuzfr3MoFNvJ5xwQqLNff7zn6fSdLV6+9nPfoaJEydGG83NmDED//jHP6LnuWprQRfFHXfcEdTX1we33XZb8MorrwQXXXRR0Ldv32D9+vWVZq0iuPrqq4NDDjkkWLt2bfRv48aN0fPPf/7zwYgRI4L58+cHzz//fHDUUUcFRx99dPR83759waGHHhrMnDkzWLx4cXD//fcHAwYMCC6//PJKvE5muP/++4Mrr7wy+Mtf/hIACO6++27q+Q033BD06dMnuOeee4IXX3wx+OhHPxqMGTMm2LVrV5Tm5JNPDiZNmhQ8/fTTweOPPx6MGzcuOOuss6Ln27ZtC5qbm4NzzjknWLp0afCHP/wh6N69e/Dzn/+8XK/pHKp6O++884KTTz6Zan9btmyh0nTFeps1a1bw61//Oli6dGmwZMmS4NRTTw1GjhwZ7NixI0rjom++9dZbQY8ePYK5c+cGr776avDjH/84qK2tDR544IGyvq8r6NTbBz7wgeCiiy6i2ty2bdui512x3v76178G9913X7B8+fJg2bJlwRVXXBF069YtWLp0aRAE+WprXVZ4mTZtWnDxxRdH1+3t7cHQoUODefPmVZCryuHqq68OJk2axH22devWoFu3bsGf/vSn6N5rr70WAAgWLlwYBEFxcqqpqQnWrVsXpfnZz34WNDU1BXv27MmU90qBnYQ7OjqCwYMHB//93/8d3du6dWvQ0NAQ/OEPfwiCIAheffXVAEDw3HPPRWn+8Y9/BIVCIXj33XeDIAiCn/70p0G/fv2oevvGN74RHHTQQRm/UXkgEl7OOOMMYR5fb0Vs2LAhABA8+uijQRC465tf//rXg0MOOYQqa/bs2cGsWbOyfqWygK23ICgKL1/60peEeXy9FdGvX7/gl7/8Ze7aWpc0G7W1tWHRokWYOXNmdK+mpgYzZ87EwoULK8hZZfHGG29g6NChGDt2LM455xysXr0aALBo0SLs3buXqq/x48dj5MiRUX0tXLgQhx12GJqbm6M0s2bNQktLC1555ZXyvkiFsHLlSqxbt46qpz59+mD69OlUPfXt2xdHHHFElGbmzJmoqanBM888E6U5/vjjUV9fH6WZNWsWli1bhvfff79Mb1N+LFiwAIMGDcJBBx2EL3zhC9i8eXP0zNdbEdu2bQMA9O/fH4C7vrlw4UKKRpims4yHbL2F+N3vfocBAwbg0EMPxeWXX47W1tboWVevt/b2dtxxxx3YuXMnZsyYkbu2VhUHM7rGpk2b0N7eTlUwADQ3N+P111+vEFeVxfTp03H77bfjoIMOwtq1a3HttdfiuOOOw9KlS7Fu3TrU19ejb9++VJ7m5masW7cOALBu3TpufYbPugLC9+TVA1lPgwYNop7X1dWhf//+VJoxY8YkaITP+vXrlwn/lcTJJ5+Mj3/84xgzZgzefPNNXHHFFTjllFOwcOFC1NbW+noD0NHRgS9/+cs45phjcOihhwKAs74pStPS0oJdu3ahe/fuWbxSWcCrNwA4++yzMWrUKAwdOhQvvfQSvvGNb2DZsmX4y1/+AqDr1tvLL7+MGTNmYPfu3ejVqxfuvvtuTJgwAUuWLMlVW+uSwotHEqecckr0e+LEiZg+fTpGjRqFP/7xj1XZAT2qC5/61Kei34cddhgmTpyI/fffHwsWLMCJJ55YQc7yg4svvhhLly7FE088UWlWqgqievvc5z4X/T7ssMMwZMgQnHjiiXjzzTex//77l5vN3OCggw7CkiVLsG3bNtx1110477zz8Oijj1aarQS6pNlowIABqK2tTXhJr1+/HoMHD64QV/lC3759ceCBB2LFihUYPHgw2trasHXrVioNWV+DBw/m1mf4rCsgfE9Zuxo8eDA2bNhAPd+3bx+2bNni65LA2LFjMWDAAKxYsQKAr7dLLrkEf//73/HII49g+PDh0X1XfVOUpqmpqaoXL6J642H69OkAQLW5rlhv9fX1GDduHKZOnYp58+Zh0qRJ+NGPfpS7ttYlhZf6+npMnToV8+fPj+51dHRg/vz5mDFjRgU5yw927NiBN998E0OGDMHUqVPRrVs3qr6WLVuG1atXR/U1Y8YMvPzyy9QE89BDD6GpqQkTJkwoO/+VwJgxYzB48GCqnlpaWvDMM89Q9bR161YsWrQoSvOvf/0LHR0d0eA5Y8YMPPbYY9i7d2+U5qGHHsJBBx1U9aYPXbzzzjvYvHkzhgwZAqDr1lsQBLjkkktw991341//+lfCLOaqb86YMYOiEaap1vFQVW88LFmyBACoNtfV6o2Hjo4O7NmzJ39tzc7/uPpxxx13BA0NDcHtt98evPrqq8HnPve5oG/fvpSXdFfCV77ylWDBggXBypUrgyeffDKYOXNmMGDAgGDDhg1BEBRD5EaOHBn861//Cp5//vlgxowZwYwZM6L8YYjcSSedFCxZsiR44IEHgoEDB3a6UOnt27cHixcvDhYvXhwACG688cZg8eLFwdtvvx0EQTFUum/fvsG9994bvPTSS8EZZ5zBDZWeMmVK8MwzzwRPPPFEcMABB1Ahv1u3bg2am5uDz3zmM8HSpUuDO+64I+jRo0dVh/zK6m379u3BV7/61WDhwoXBypUrg4cffjg4/PDDgwMOOCDYvXt3RKMr1tsXvvCFoE+fPsGCBQuokN7W1tYojYu+GYavfu1rXwtee+214Oabb67qkF9Vva1YsSK47rrrgueffz5YuXJlcO+99wZjx44Njj/++IhGV6y3yy67LHj00UeDlStXBi+99FJw2WWXBYVCIXjwwQeDIMhXW+uywksQBMGPf/zjYOTIkUF9fX0wbdq04Omnn640SxXD7NmzgyFDhgT19fXBsGHDgtmzZwcrVqyInu/atSv44he/GPTr1y/o0aNH8LGPfSxYu3YtRWPVqlXBKaecEnTv3j0YMGBA8JWvfCXYu3dvuV8lUzzyyCMBgMS/8847LwiCYrj0t771raC5uTloaGgITjzxxGDZsmUUjc2bNwdnnXVW0KtXr6CpqSmYM2dOsH37dirNiy++GBx77LFBQ0NDMGzYsOCGG24o1ytmAlm9tba2BieddFIwcODAoFu3bsGoUaOCiy66KLGQ6Ir1xqszAMGvf/3rKI2rvvnII48EkydPDurr64OxY8dSZVQbVPW2evXq4Pjjjw/69+8fNDQ0BOPGjQu+9rWvUfu8BEHXq7fPfvazwahRo4L6+vpg4MCBwYknnhgJLkGQr7ZWCIIgMNPVeHh4eHh4eHhUDl3S58XDw8PDw8OjeuGFFw8PDw8PD4+qghdePDw8PDw8PKoKXnjx8PDw8PDwqCp44cXDw8PDw8OjquCFFw8PDw8PD4+qghdePDw8PDw8PKoKXnjx8PDw8PDwqCp44cXDw8PDw8OjquCFFw8PDw8PD4+qghdePDw8PDw8PKoKXnjx8PDw8PDwqCr8fwbVQ29J0YRLAAAAAElFTkSuQmCC",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "percent = [e[3] for e in episodes[0]]\n",
    "plt.plot(list(range(len(percent))), percent)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(list(range(len(env_rand_post_training.portfolio_return_memory\n",
    "\n",
    "))), env_rand_post_training.asset_memory, label=\"random\"\n",
    ")\n",
    "plt.plot(list(range(len(env_nstep_sarsa_post_training.portfolio_return_memory\n",
    "\n",
    "))), env_nstep_sarsa_post_training.asset_memory, label=\"n-step sarsa\"\n",
    "\n",
    ")\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[<matplotlib.lines.Line2D at 0x7f78b1573a90>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b1573670>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b1573970>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495ec20>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495d900>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495e650>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495e050>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495e980>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495fdc0>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495e380>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495d4b0>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495d5a0>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495f7c0>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495f760>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495f4c0>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495e620>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495faf0>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495d990>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495d9c0>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495f940>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495fe80>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495d810>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495ca30>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495c9d0>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495c640>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495c760>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495c0d0>,\n",
       " <matplotlib.lines.Line2D at 0x7f78b495c490>]"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(env_nstep_sarsa_post_training.actions_memory)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "FinRL",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}