Welcome to CleanMARL documentation!

CleanMARL provides single file implementations of Deep Multi-Agent Reinforcement Learning (MARL) algorithms. In addition, it serves as an educational resource for learning the algorithms and implementations of MARL. In a nutshell this project is a combination of CleanRL and Spinning Up in Deep RL but for multi-agent RL.

Github repository: https://github.com/AmineAndam04/cleanmarl

Main Features

  • Implementations of key MARL algorithms: VDN, QMIX, COMA, MADDPG, FACMAC, IPPO, and MAPPO.

  • A documentation for algorithms, code and training details.

  • We support parallel environments and recurrent policies.

  • Tensorboard and Weights & Biases logging.

Contents