andri27-ts/Reinforcement-Learning
A 60-day deep reinforcement learning course covering q learning, DQN, PPO, and actor critic with PyTorch implementations.
Velocity · 7d
+1.7
★ / day
Trend
→steady
star history
This repository is a comprehensive educational course on deep reinforcement learning combining neural networks with RL algorithms. It provides lecture content from DeepMind and Berkeley alongside working implementations of key algorithms including DQN, A2C, PPO, and policy gradients. Code is written in Python using PyTorch and tested on OpenAI Gym environments including RoboSchool and Atari.