- Creating Pro-Level AI for a Real-Time Fighting Game Using Deep Reinforcement Learning, NCSoft, 2021
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments, OpenAI, 2020
- Value-Decomposition Networks For Cooperative Multi-Agent Learning, DeepMind, 2017
- Human-level performance in first-person multiplayer games with population-based deep reinforcement learning, DeepMind, 2018
- Emergent Tool Use From Multi-Agent Autocurricula, OpenAI, 2020
- Data 2 with Large Scale Deep Reinforcment Learning, OpenAI, 2021
- Sub-Policy Adaptation for Hierarchical Reinforcement Learning, UC Berkeley, 2020
- ROMA: Multi-Agent Reinforcement Learning with Emergent Roles, Tsinghua Univ, 2020