机器人 / 具身智能

LPPG-RL: Lexicographically Projected Policy Gradient Reinforcement Learning with Subproblem Exploration

Ruiyu Qiu, Rui Wang, Guanghui Yang, Xiang Li, Zhijiang Shao

专题命中 模仿学习与强化学习 ：navigation(abstract)；分类 cs.AI、cs.LG

Balance Equation-based Distributionally Robust Offline Imitation Learning

Rishabh Agrawal, Yusuf Alvi, Rahul Jain, Ashutosh Nayyar

机构 * University of Southern California（南加州大学） 纠错

专题命中 模仿学习与强化学习 ：robotic(abstract)；分类 cs.AI、cs.LG

On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision Transformers

Miroslav Štrupl, Oleg Szehr, Francesco Faccio, Dylan R. Ashley, Rupesh Kumar Srivastava, Jürgen Schmidhuber

机构 * Dalle Molle Institute for Artificial Intelligence (IDSIA) - USI/SUPSI（达摩信息技术研究所（IDSIA）- USI/SUPSI） ； Center of Excellence for Generative AI, King Abdullah University of Science and Technology（生成人工智能卓越中心，国王阿卜杜勒阿齐兹大学科学与技术学院） ； NNAISENSE 纠错

专题命中 模仿学习与强化学习 ：robotic(abstract)；分类 cs.AI、cs.LG

Comments 85 pages in main text + 4 pages of references + 26 pages of appendices, 12 figures in main text + 2 figures in appendices; source code available at https://github.com/struplm/eUDRL-GCSL-ODT-Convergence-public

AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress

Zhiheng Xi, Chenyang Liao, Guanyu Li, Yajie Yang, Wenxiang Chen, Zhihao Zhang, Binghai Wang, Senjie Jin, Yuhao Zhou, Jian Guan, Wei Wu, Tao Ji, Tao Gui, Qi Zhang, Xuanjing Huang

机构 * Fudan University（复旦大学） ； Ant Group（蚂蚁集团） 纠错

专题命中 模仿学习与强化学习 ：navigation(abstract)；分类 cs.LG

Comments Preprint