Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

Multi-Agent Reinforcement Learning with JAX

Really Fast End-to-End Jax RL Implementations

SMAC: The StarCraft Multi-Agent Challenge

Fine-tuned MARL algorithms on SMAC (100% win rates on most scenarios)

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Mastering Diverse Domains through World Models

The Statcraft Multi-Agent challenge lite

Baselines for gymnax 🤖

Implementations of robust Dual Curriculum Design (DCD) algorithms for unsupervised environment design.

[ICML 2021] DFAC Framework: Factorizing the Value Function via Quantile Mixture for Multi-Agent Distributional Q-Learning

Code for "Randomized Entity-wise Factorization for Multi-Agent Reinforcement Learning" ICML 2021

An extension of the PyMARL codebase that includes additional algorithms and environment support

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

This is the official implementation of Multi-Agent PPO (MAPPO).

Transfer Thesis

Hello, I pushed some python environments for Multi Agent Reinforcement Learning.

CDT Challenge 2021: Autonomous exploration with wheeled robots