Deep Q-Learning Network using PyTorch

This project implements agent training using the Proximal Policy Optimization (PPO) algorithm in the BipedalWalker-v3 environment at two difficulty levels: normal and hardcore. The model's performance is evaluated based on rewards collected during the training process.

Nokia's classic 'snake' game, written in NumPy and converted into a Gymnasium Environment() for use with gradient-based reinforcement learning algorithms

Experiments with Dyna-Q

This project implements a Deep Q-Network (DQN) using PyTorch to train an agent to play Atari's Ms. Pac-Man. It utilizes reinforcement learning with a convolutional neural network (CNN) for image processing. Features include experience replay, frame preprocessing, and CUDA support, with trained model saving and video rendering of gameplay.

A Gymnasium environment and RL algorithms for navigation on human arms using ultrasound/MRI

using gymnasium (gymnasium.farma.org) to create a box2d environment of lunar lander and training it using Deep Q-learning for lunar landing

Gymnasium environment based on real room and robot

Training reinforcement learning agents to control a car in the Car-2D environment using Gymnasium.

Using Q-Learning methods in Gymnasium to solve various games, very basic implementation.

A command line tool for generating an unlimited number of RDDL instance files of customisable complexity.

Lunar Lander envitoment of gymnasium solved using Double DQN and D3QN

A sailing environment for OpenAI Gym / Gymnasium

Green-DCC is a benchmark environment for evaluating dynamic workload distribution techniques for sustainable Data Center Clusters (DCC) using reinforcement learning and other control algorithms.

A Complete Collection of Deep RL Famous Algorithms implemented in Gymnasium most Popular environments

Automated stock trading strategy using deep reinforcement learning and recurrent neural networks

Repository contains codes for the course CS780: Deep Reinforcement Learning

Spatio-temporal wildlife management Gymnasium RL Environment created and trained on for my Master's thesis

Game for up to two RL agents. Environment build on Gymnasium