tianshou

Adversarial attacks on Deep Reinforcement Learning (RL)

Provide full reinforcement learning benchmark on mujoco environments, including ddpg, sac, td3, pg, a2c, ppo, library

OpenAI Gym environment solutions using Deep Reinforcement Learning.

Interactive Multi-Agent Reinforcement Learning Environment for the board game Gobblet using PettingZoo.

Automatic code generator for training Reinforcement Learning policies

Robo-Chess, a comprehensive repository dedicated to developing chess engines using a variety of Deep Reinforcement Learning techniques

基于Tianshou框架的强化学习DRL实验探索(在gym,pettingzoo,atari等环境)

De novo cyclic protein polypeptide design using reinforcement learning.

Robotic simulation platform for AI-based manipulation with Franka Panda, ROS 2 Humble, Gazebo Ignition Fortress, MoveIt 2, SAC+HER reinforcement learning and ACT/LeRobot imitation learning.

Multi-Agent DRL task analysed as a part of a course project for CS698R-21, IITK

Best Agents in a Simplified Environment called "Naive Bandori". Agents with or without audio inputs are both available.

Simulation a board game with reinforcement learning.

Reinforcement learning agents for Connect4, featuring a robust AlphaZero implementation from scratch. Includes Rainbow DQN, PPO, and classic search algorithms like MCTS and Minimax, aiming to benchmark different strategies and agent architectures.