Research
My research interests lie in deep reinforcement learning, multi-agent reinforcement learning and robotics,
with the goal of robots being able to collaborate, explore and learn like human beings.
|
|
OpenRL: an open-source reinforcement learning research framework
Shiyu Huang,
Wentse Chen,
Yiwen Sun,
Fuqing Bie,
Wei-Wei Tu
Supports single-agent and multi-agent RL algorithms, natural language tasks(RLHF), self-play training.
|
|
DGPO: Discovering Multiple Strategies with Diversity-Guided Policy Optimization
Wentse Chen,
Shiyu Huang,
Yuan Chiang,
Tim Pearce,
Wei-Wei Tu,
Chen Ting,
Zhu Jun,
The 38th Annual AAAI Conference on Artificial Intelligence (AAAI2024)
Proposed an on-policy framework for discovering multiple strategies for the same task in a single training process.
|
|
TiZero: Mastering Multi-Agent Football with Curriculum Learning and Self-Play
Fanqi Lin*,
Shiyu Huang*,
Tim Pearce,
Wentse Chen,
Wei-Wei Tu
The 22nd International Conference on Autonomous Agents and Multiagent Systems(AAMAS2023)
Created an on-policy MARL algorithm, along with an adaptive curriculum learning approach and a unique self-play strategy, for excelling in the Google Research Football game.
|
TiKick: Towards Playing Multi-agent Football Full Games from Single-agent Demonstrations
Shiyu Huang*,
Wentse Chen*,
Longfei Zhang,
Shizhen Xu,
Ziyang Li,
Fengming Zhu,
Deheng Ye,
Ting Chen,
Jun Zhu
NeurIPS-21 Workshop: 2nd Offline Reinforcement Learning Workshop
Developed a distributed learning system and new offline algorithms to learn a powerful multi-agent AI from the fixed single-agent dataset.
|
|