Deep Reinforcement Learing with Pytorch

This repository converts Tensorflow code of the book Deep Reinforcement Learning with Python (authored by Sudharsan Ravichandiran, 2nd edition) into Pytorch version.

Versions

• Ubuntu 20.04
• CUDA 12.0
• Python 3.9
• Pytorch 1.12.0
• Gym

Components

Chapter 9

• Deep-Q learning (DQN)

Chapter 10

• Policy Gradient (PG)

Chapter 11

• Multi-Agent Actor-Ctiric (A3C)

Chapter 12

• Deep Deterministic Policy Gradient (DDPG)
• Soft Action-Critic (SAC)
• Twin-Delayed DDPG (TD3)

Chapter 13

in progress

• Trust Region Policy Optimization (TRPO)
• Proximal Policy Optimization Algorithm (PPO)