5 papers
Of Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents
Xingjian Diao, Tianyu Yang, Wenjun Huang +8
Reinforcement learning improves tool-use agents, yet fine-grained credit assignment remains challenging even with step-level feedback. An observed error may be inherited from an ea…
Can the Environment Speak for Itself? -GRPO: A Turn-Trajectory Group Relative Policy Optimization for Caregiver Agents
Yutong Song, Jiang Wu, Pengfei Zhang +4
Optimizing large language models (LLMs) for long-horizon caregiver agents requires balancing delayed task objectives with immediate environment dynamics, such as patient distress a…
Effective Reinforcement Learning Control using Conservative Soft Actor-Critic
Zhiwei Shang, Xinyi Yuan, Wenjun Huang +3
Reinforcement Learning (RL) has shown great potential in complex control tasks, particularly when combined with deep neural networks within the Actor-Critic (AC) framework. However…
Multi-Goal Dexterous Hand Manipulation using Probabilistic Model-based Reinforcement Learning
Yingzhuo Jiang, Wenjun Huang, Rongdun Lin +3
This paper tackles the challenge of learning multi-goal dexterous hand manipulation tasks using model-based Reinforcement Learning. We propose Goal-Conditioned Probabilistic Model…
Practical Probabilistic Model-based Deep Reinforcement Learning by Integrating Dropout Uncertainty and Trajectory Sampling
Wenjun Huang, Yunduan Cui, Huiyun Li +1
This paper addresses the prediction stability, prediction accuracy and control capability of the current probabilistic model-based reinforcement learning (MBRL) built on neural net…