MALib: A Parallel Framework for Population-based Multi-agent Reinforcement Learning. Preprint, 2021.

PDF Code Project

Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems. Blue Sky Track, AAMAS, Best Paper Award, 2021.


Learning in Nonzero-Sum Stochastic Games with Potentials. ICML, 2021.


Multi-Agent Determinantal Q-Learning. ICML, 2020.

Code Arxiv

SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving. CoRL, Best System Paper Award, 2020.

Code PDF

A Regularized Opponent Model with Maximum Entropy Objective. IJCAI, 2019.

Preprint PDF Code

Learning to Design Games: Strategic Environments in Deep Reinforcement Learning. IJCAI, 2018.

PDF Arxiv

A Study of AI Population Dynamics with Million-agent Reinforcement Learning. AAMAS, 2018.

PDF Code Arxiv

Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games. NIPS17 Emergent Communication Workshop, 2017.

PDF Code

Product-based Neural Networks for User Response Prediction. ICDM, 2016.

PDF Code