Popular GitHub Repositories for Atari2600

JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"

An implementation of (Double/Dueling) Deep-Q Learning to play Super Mario Bros.

Code for "Spinning Up a Pong AI With Deep RL" on FloydHub.

Code from "How useful is quantilization for mitigating specification-gaming?"

Pytorch implementation of the Persistent Advantage reinforcement learning operator proposed in paper 'Increasing the Action Gap: New Operators for Reinforcement Learning'. This repository includes source code for training, demo, action gap visualization and trained models for 5 Atari games.

Example Noisy DQN implementation with ReLAx

Example Double DQN implementation with ReLAx

Example Categorical DQN implementation with ReLAx

Example DQN implementation with ReLAx

Deep reinforcement learning for self made atari game environment

Example Dueling DQN implementation with ReLAx

Training PPO with DQN as a critic