3 papers
cs.RO2026
From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
Sichang Su, Benjamin Yang, Zhiyun Deng +4
A pretrained robot foundation policy may execute most of a long-horizon task yet repeatedly fail at a few critical subtasks. Collecting additional full-task demonstrations for supe…
cs.RO2025
ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
Tonghe Zhang, Chao Yu, Sichang Su +1
We propose ReinFlow, a simple yet effective online reinforcement learning (RL) framework that fine-tunes a family of flow matching policies for continuous robotic control. Derived…
cs.LG2024
Hybrid Training for Enhanced Multi-task Generalization in Multi-agent Reinforcement Learning
Mingliang Zhang, Sichang Su, Chengyang He +1
In multi-agent reinforcement learning (MARL), achieving multi-task generalization to diverse agents and objectives presents significant challenges. Existing online MARL algorithms…