-
Notifications
You must be signed in to change notification settings - Fork 225
/
gym-DQN.py
477 lines (399 loc) · 16.1 KB
/
gym-DQN.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
# -*- coding: utf-8 -*-
"""
Reinforcement Learning (DQN) tutorial
=====================================
**Author**: `Adam Paszke <https://github.com/apaszke>`_
This tutorial shows how to use PyTorch to train a Deep Q Learning (DQN) agent
on the CartPole-v0 task from the `OpenAI Gym <https://gym.openai.com/>`__.
**Task**
The agent has to decide between two actions - moving the cart left or
right - so that the pole attached to it stays upright. You can find an
official leaderboard with various algorithms and visualizations at the
`Gym website <https://gym.openai.com/envs/CartPole-v0>`__.
.. figure:: /_static/img/cartpole.gif
:alt: cartpole
cartpole
As the agent observes the current state of the environment and chooses
an action, the environment *transitions* to a new state, and also
returns a reward that indicates the consequences of the action. In this
task, the environment terminates if the pole falls over too far.
The CartPole task is designed so that the inputs to the agent are 4 real
values representing the environment state (position, velocity, etc.).
However, neural networks can solve the task purely by looking at the
scene, so we'll use a patch of the screen centered on the cart as an
input. Because of this, our results aren't directly comparable to the
ones from the official leaderboard - our task is much harder.
Unfortunately this does slow down the training, because we have to
render all the frames.
Strictly speaking, we will present the state as the difference between
the current screen patch and the previous one. This will allow the agent
to take the velocity of the pole into account from one image.
**Packages**
First, let's import needed packages. Firstly, we need
`gym <https://gym.openai.com/docs>`__ for the environment
(Install using `pip install gym`).
We'll also use the following from PyTorch:
- neural networks (``torch.nn``)
- optimization (``torch.optim``)
- automatic differentiation (``torch.autograd``)
- utilities for vision tasks (``torchvision`` - `a separate
package <https://github.com/pytorch/vision>`__).
"""
import gym
import math
import random
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
from collections import namedtuple
from itertools import count
from copy import deepcopy
from PIL import Image
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.autograd import Variable
import torchvision.transforms as T
env = gym.make('CartPole-v0').unwrapped
# set up matplotlib
is_ipython = 'inline' in matplotlib.get_backend()
if is_ipython:
from IPython import display
plt.ion()
# if gpu is to be used
use_cuda = torch.cuda.is_available()
FloatTensor = torch.cuda.FloatTensor if use_cuda else torch.FloatTensor
LongTensor = torch.cuda.LongTensor if use_cuda else torch.LongTensor
ByteTensor = torch.cuda.ByteTensor if use_cuda else torch.ByteTensor
Tensor = FloatTensor
######################################################################
# Replay Memory
# -------------
#
# We'll be using experience replay memory for training our DQN. It stores
# the transitions that the agent observes, allowing us to reuse this data
# later. By sampling from it randomly, the transitions that build up a
# batch are decorrelated. It has been shown that this greatly stabilizes
# and improves the DQN training procedure.
#
# For this, we're going to need two classses:
#
# - ``Transition`` - a named tuple representing a single transition in
# our environment
# - ``ReplayMemory`` - a cyclic buffer of bounded size that holds the
# transitions observed recently. It also implements a ``.sample()``
# method for selecting a random batch of transitions for training.
#
Transition = namedtuple('Transition',
('state', 'action', 'next_state', 'reward'))
class ReplayMemory(object):
def __init__(self, capacity):
self.capacity = capacity
self.memory = []
self.position = 0
def push(self, *args):
"""Saves a transition."""
if len(self.memory) < self.capacity:
self.memory.append(None)
self.memory[self.position] = Transition(*args)
self.position = (self.position + 1) % self.capacity
def sample(self, batch_size):
return random.sample(self.memory, batch_size)
def __len__(self):
return len(self.memory)
######################################################################
# Now, let's define our model. But first, let quickly recap what a DQN is.
#
# DQN algorithm
# -------------
#
# Our environment is deterministic, so all equations presented here are
# also formulated deterministically for the sake of simplicity. In the
# reinforcement learning literature, they would also contain expectations
# over stochastic transitions in the environment.
#
# Our aim will be to train a policy that tries to maximize the discounted,
# cumulative reward
# :math:`R_{t_0} = \sum_{t=t_0}^{\infty} \gamma^{t - t_0} r_t`, where
# :math:`R_{t_0}` is also known as the *return*. The discount,
# :math:`\gamma`, should be a constant between :math:`0` and :math:`1`
# that ensures the sum converges. It makes rewards from the uncertain far
# future less important for our agent than the ones in the near future
# that it can be fairly confident about.
#
# The main idea behind Q-learning is that if we had a function
# :math:`Q^*: State \times Action \rightarrow \mathbb{R}`, that could tell
# us what our return would be, if we were to take an action in a given
# state, then we could easily construct a policy that maximizes our
# rewards:
#
# .. math:: \pi^*(s) = \arg\!\max_a \ Q^*(s, a)
#
# However, we don't know everything about the world, so we don't have
# access to :math:`Q^*`. But, since neural networks are universal function
# approximators, we can simply create one and train it to resemble
# :math:`Q^*`.
#
# For our training update rule, we'll use a fact that every :math:`Q`
# function for some policy obeys the Bellman equation:
#
# .. math:: Q^{\pi}(s, a) = r + \gamma Q^{\pi}(s', \pi(s'))
#
# The difference between the two sides of the equality is known as the
# temporal difference error, :math:`\delta`:
#
# .. math:: \delta = Q(s, a) - (r + \gamma \max_a Q(s', a))
#
# To minimise this error, we will use the `Huber
# loss <https://en.wikipedia.org/wiki/Huber_loss>`__. The Huber loss acts
# like the mean squared error when the error is small, but like the mean
# absolute error when the error is large - this makes it more robust to
# outliers when the estimates of :math:`Q` are very noisy. We calculate
# this over a batch of transitions, :math:`B`, sampled from the replay
# memory:
#
# .. math::
#
# \mathcal{L} = \frac{1}{|B|}\sum_{(s, a, s', r) \ \in \ B} \mathcal{L}(\delta)
#
# .. math::
#
# \text{where} \quad \mathcal{L}(\delta) = \begin{cases}
# \frac{1}{2}{\delta^2} & \text{for } |\delta| \le 1, \\
# |\delta| - \frac{1}{2} & \text{otherwise.}
# \end{cases}
#
# Q-network
# ^^^^^^^^^
#
# Our model will be a convolutional neural network that takes in the
# difference between the current and previous screen patches. It has two
# outputs, representing :math:`Q(s, \mathrm{left})` and
# :math:`Q(s, \mathrm{right})` (where :math:`s` is the input to the
# network). In effect, the network is trying to predict the *quality* of
# taking each action given the current input.
#
class DQN(nn.Module):
def __init__(self):
super(DQN, self).__init__()
self.conv1 = nn.Conv2d(3, 16, kernel_size=5, stride=2)
self.bn1 = nn.BatchNorm2d(16)
self.conv2 = nn.Conv2d(16, 32, kernel_size=5, stride=2)
self.bn2 = nn.BatchNorm2d(32)
self.conv3 = nn.Conv2d(32, 32, kernel_size=5, stride=2)
self.bn3 = nn.BatchNorm2d(32)
self.head = nn.Linear(448, 2)
def forward(self, x):
x = F.relu(self.bn1(self.conv1(x)))
x = F.relu(self.bn2(self.conv2(x)))
x = F.relu(self.bn3(self.conv3(x)))
return self.head(x.view(x.size(0), -1))
######################################################################
# Input extraction
# ^^^^^^^^^^^^^^^^
#
# The code below are utilities for extracting and processing rendered
# images from the environment. It uses the ``torchvision`` package, which
# makes it easy to compose image transforms. Once you run the cell it will
# display an example patch that it extracted.
#
resize = T.Compose([T.ToPILImage(),
T.Scale(40, interpolation=Image.CUBIC),
T.ToTensor()])
# This is based on the code from gym.
screen_width = 600
def get_cart_location():
world_width = env.x_threshold * 2
scale = screen_width / world_width
return int(env.state[0] * scale + screen_width / 2.0) # MIDDLE OF CART
def get_screen():
screen = env.render(mode='rgb_array').transpose(
(2, 0, 1)) # transpose into torch order (CHW)
# Strip off the top and bottom of the screen
screen = screen[:, 160:320]
view_width = 320
cart_location = get_cart_location()
if cart_location < view_width // 2:
slice_range = slice(view_width)
elif cart_location > (screen_width - view_width // 2):
slice_range = slice(-view_width, None)
else:
slice_range = slice(cart_location - view_width // 2,
cart_location + view_width // 2)
# Strip off the edges, so that we have a square image centered on a cart
screen = screen[:, :, slice_range]
# Convert to float, rescare, convert to torch tensor
# (this doesn't require a copy)
screen = np.ascontiguousarray(screen, dtype=np.float32) / 255
screen = torch.from_numpy(screen)
# Resize, and add a batch dimension (BCHW)
return resize(screen).unsqueeze(0).type(Tensor)
env.reset()
plt.figure()
plt.imshow(get_screen().cpu().squeeze(0).permute(1, 2, 0).numpy(),
interpolation='none')
plt.title('Example extracted screen')
plt.show()
######################################################################
# Training
# --------
#
# Hyperparameters and utilities
# ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
# This cell instantiates our model and its optimizer, and defines some
# utilities:
#
# - ``Variable`` - this is a simple wrapper around
# ``torch.autograd.Variable`` that will automatically send the data to
# the GPU every time we construct a Variable.
# - ``select_action`` - will select an action accordingly to an epsilon
# greedy policy. Simply put, we'll sometimes use our model for choosing
# the action, and sometimes we'll just sample one uniformly. The
# probability of choosing a random action will start at ``EPS_START``
# and will decay exponentially towards ``EPS_END``. ``EPS_DECAY``
# controls the rate of the decay.
# - ``plot_durations`` - a helper for plotting the durations of episodes,
# along with an average over the last 100 episodes (the measure used in
# the official evaluations). The plot will be underneath the cell
# containing the main training loop, and will update after every
# episode.
#
BATCH_SIZE = 128
GAMMA = 0.999
EPS_START = 0.9
EPS_END = 0.05
EPS_DECAY = 200
model = DQN()
if use_cuda:
model.cuda()
optimizer = optim.RMSprop(model.parameters())
memory = ReplayMemory(10000)
steps_done = 0
def select_action(state):
global steps_done
sample = random.random()
eps_threshold = EPS_END + (EPS_START - EPS_END) * \
math.exp(-1. * steps_done / EPS_DECAY)
steps_done += 1
if sample > eps_threshold:
return model(
Variable(state, volatile=True).type(FloatTensor)).data.max(1)[1].view(1, 1)
else:
return LongTensor([[random.randrange(2)]])
episode_durations = []
def plot_durations():
plt.figure(2)
plt.clf()
durations_t = torch.FloatTensor(episode_durations)
plt.title('Training...')
plt.xlabel('Episode')
plt.ylabel('Duration')
plt.plot(durations_t.numpy())
# Take 100 episode averages and plot them too
if len(durations_t) >= 100:
means = durations_t.unfold(0, 100, 1).mean(1).view(-1)
means = torch.cat((torch.zeros(99), means))
plt.plot(means.numpy())
plt.pause(0.001) # pause a bit so that plots are updated
if is_ipython:
display.clear_output(wait=True)
display.display(plt.gcf())
######################################################################
# Training loop
# ^^^^^^^^^^^^^
#
# Finally, the code for training our model.
#
# Here, you can find an ``optimize_model`` function that performs a
# single step of the optimization. It first samples a batch, concatenates
# all the tensors into a single one, computes :math:`Q(s_t, a_t)` and
# :math:`V(s_{t+1}) = \max_a Q(s_{t+1}, a)`, and combines them into our
# loss. By defition we set :math:`V(s) = 0` if :math:`s` is a terminal
# state.
last_sync = 0
def optimize_model():
global last_sync
if len(memory) < BATCH_SIZE:
return
transitions = memory.sample(BATCH_SIZE)
# Transpose the batch (see http://stackoverflow.com/a/19343/3343043 for
# detailed explanation).
batch = Transition(*zip(*transitions))
# Compute a mask of non-final states and concatenate the batch elements
non_final_mask = ByteTensor(tuple(map(lambda s: s is not None,
batch.next_state)))
# We don't want to backprop through the expected action values and volatile
# will save us on temporarily changing the model parameters'
# requires_grad to False!
non_final_next_states = Variable(torch.cat([s for s in batch.next_state
if s is not None]),
volatile=True)
state_batch = Variable(torch.cat(batch.state))
action_batch = Variable(torch.cat(batch.action))
reward_batch = Variable(torch.cat(batch.reward))
# Compute Q(s_t, a) - the model computes Q(s_t), then we select the
# columns of actions taken
state_action_values = model(state_batch).gather(1, action_batch)
# Compute V(s_{t+1}) for all next states.
next_state_values = Variable(torch.zeros(BATCH_SIZE).type(Tensor))
next_state_values[non_final_mask] = model(non_final_next_states).max(1)[0]
# Now, we don't want to mess up the loss with a volatile flag, so let's
# clear it. After this, we'll just end up with a Variable that has
# requires_grad=False
next_state_values.volatile = False
# Compute the expected Q values
expected_state_action_values = (next_state_values * GAMMA) + reward_batch
# Compute Huber loss
loss = F.smooth_l1_loss(state_action_values, expected_state_action_values)
# Optimize the model
optimizer.zero_grad()
loss.backward()
for param in model.parameters():
param.grad.data.clamp_(-1, 1)
optimizer.step()
######################################################################
#
# Below, you can find the main training loop. At the beginning we reset
# the environment and initialize the ``state`` variable. Then, we sample
# an action, execute it, observe the next screen and the reward (always
# 1), and optimize our model once. When the episode ends (our model
# fails), we restart the loop.
#
# Below, `num_episodes` is set small. You should download
# the notebook and run lot more epsiodes.
num_episodes = 1000
for i_episode in range(num_episodes):
# Initialize the environment and state
env.reset()
last_screen = get_screen()
current_screen = get_screen()
state = current_screen - last_screen
for t in count():
# Select and perform an action
action = select_action(state)
_, reward, done, _ = env.step(action[0, 0])
reward = Tensor([reward])
# Observe new state
last_screen = current_screen
current_screen = get_screen()
if not done:
next_state = current_screen - last_screen
else:
next_state = None
# Store the transition in memory
memory.push(state, action, next_state, reward)
# Move to the next state
state = next_state
# Perform one step of the optimization (on the target network)
optimize_model()
if done:
print('Episode %02i, Duration %i' % (i_episode, t+1))
episode_durations.append(t + 1)
plot_durations()
break
print('Complete')
env.render(close=True)
env.close()
plt.ioff()
plt.show()