6 papers
Interactive Inverse Reinforcement Learning of Interaction Scenarios via Bi-level Optimization
Yue Mao, Shicheng Liu, Siyuan Xu +1
Inverse reinforcement learning (IRL) learns a reward function and a corresponding policy that best fit the demonstration data of an expert. However, in the current IRL setting, the…
DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models
Siyuan Xu, Tianshi Wang, Fengling Li +2
Vision-Language-Action models (VLAs) have demonstrated strong potential for embodied AI, yet their deployment on resource-limited robots remains challenging due to high memory and…
Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning
Siyuan Xu, Shiyang Li, Xin Liu +9
Existing synthetic tool-use corpora are primarily designed for offline supervised fine-tuning, yet reinforcement learning (RL) requires executable environments that support reward-…
MaP-AVR: A Meta-Action Planner for Agents Leveraging Vision Language Models and Retrieval-Augmented Generation
Zhenglong Guo, Yiming Zhao, Feng Jiang +4
Embodied robotic AI systems designed to manage complex daily tasks rely on a task planner to understand and decompose high-level tasks. While most research focuses on enhancing the…
Explainable reinforcement learning from human feedback to improve alignment
Shicheng Liu, Siyuan Xu, Wenjie Qiu +2
A common and effective strategy for humans to improve an unsatisfactory outcome in daily life is to find a cause of this outcome and correct the cause. In this paper, we investigat…
Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator
Siyuan Xu, Minghui Zhu
Meta-reinforcement learning (Meta-RL) has attracted attention due to its capability to enhance reinforcement learning (RL) algorithms, in terms of data efficiency and generalizabil…