abhraIITKgp/RL-Notes-and-DQN-on-Atari-Breakour-and-Pong

Reinforcement-Learning-David-Silver-My_Notes

This repository provides code, exercises and solutions for popular Reinforcement Learning algorithms which I learned during my summer break. I finally implemented Pong and Atari breakout games using DQN algorithms. Implementations of these using Double-DQN and A3C algorithms would be pushed soon. These are meant to serve as a learning tool to complement the theoretical materials I learnt from:-

• Reinforcement Learning: An Introduction (2nd Edition)
• David Silver's Reinforcement Learning Course

Each folder in corresponds to one or more chapters of the above textbook and/or course. In addition to exercises and solution, each folder also contains a list of learning goals, a brief concept summary I wrote while learning, and links to the relevant readings.

All code is written in Python 3 and uses RL environments from OpenAI Gym. Advanced techniques use Pytorch for neural network implementations.

Resources

Textbooks:

• Reinforcement Learning: An Introduction (2nd Edition)

Other Useful Online Class:

• CS285 - Deep Reinforcement Learning (Berkeley, Fall 2020)