4 papers
Many Ways to Succeed: Diversity-Driven RL Fine-Tuning for VLA Generalization
Haoru Li, Jinmei Liu, Zhiyong Wang +5
Reinforcement learning (RL) fine-tuning improves vision-language-action (VLA) policies through closed-loop experience, yet generalization beyond the fine-tuning distribution remain…
Conditional Diffusion Model for Multi-Agent Dynamic Task Decomposition
Yanda Zhu, Yuanyang Zhu, Daoyi Dong +2
Task decomposition has shown promise in complex cooperative multi-agent reinforcement learning (MARL) tasks, which enables efficient hierarchical learning for long-horizon tasks in…
Mixture-of-Experts Meets In-Context Reinforcement Learning
Wenhao Wu, Fuhong Liu, Haoru Li +4
In-context reinforcement learning (ICRL) has emerged as a promising paradigm for adapting RL agents to downstream tasks through prompt conditioning. However, two notable challenges…
Learning Diverse Natural Behaviors for Enhancing the Agility of Quadrupedal Robots
Huiqiao Fu, Haoyu Dong, Wentao Xu +5
Achieving animal-like agility is a longstanding goal in quadrupedal robotics. While recent studies have successfully demonstrated imitation of specific behaviors, enabling robots t…