Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning

作者：Jinzong Dong, Wei Huang, Jianshu Zhang, Zhuo Chen, Xinzhe Yuan, Qinying Gu, Zhaohui Jiang, Nanyang Ye · 单位：School of Automation, Central South University, Changsha, China, Shanghai AI Laboratory, Shanghai, China, Shanghai Jiao Tong University, Shanghai, China · 会议/期刊：arXiv · 日期：2026-02-07 · 来源：Low-Level Learning-Based Action Modelling / Learning Strategy / Model-free Reinforcement Learning / RL in Fine-Tuning