Awesome Robotics Manipulation · full_paper

DEAS: DEtached value learning with Action Sequence for Scalable Offline RL

作者：Changyeon Kim, Haeone Lee, Younggyo Seo, Kimin Lee, Yuke Zhu · 单位：KAIST, UC Berkeley University of Texas at Austin NVIDIA · 会议/期刊：ICLR 2026 · 日期：2025-10-09 · 来源：Low-Level Learning-Based Action Modelling / Learning Strategy / Model-free Reinforcement Learning / RL in Pre-Training

强化学习触觉基础模型机器人学习
新标签打开 AlphaXiv新标签打开 Paper新标签打开 Code
DEAS: DEtached value learning with Action Sequence for Scalable Offline RL figure
AlphaXiv 中文论文页面（可滚动查看）