Publications

(2021). MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research. In NeurIPS 2021.

PDF Code Blogpost Documentation

(2021). Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning. In ICML 2021.

PDF

(2020). Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning. Journal of Machine Learning Research.

PDF Code

(2019). MAVEN: Multi-Agent Variational Exploration. In NeurIPS 2019.

PDF Code

(2019). The StarCraft Multi-Agent Challenge. In AAMAS 2019.

PDF Code Benchmark Blogpost

(2018). QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning. In ICML 2018.

PDF Code Video

Code

MiniHack

A sandbox framework for designing rich and diverse environments for RL.

PyMARL

A framework for deep multi-agent RL research written in PyTorch.

SMAC

A benchmark for cooperative multi-agent RL based on StarCraft II.

Contact