机器人 / 具身智能 - arXivDaily 专题

2509.04063 2025-09-05 cs.RO cs.LG 73%

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models

Hongyin Zhang, Shiyuan Zhang, Junxi Jin, Qixin Zeng, Yifan Qiao, Hongchao Lu, Donglin Wang

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

2508.14120 2025-08-21 cs.RO cs.AI 73%

SimGenHOI: Physically Realistic Whole-Body Humanoid-Object Interaction via Generative Modeling and Reinforcement Learning

Yuhang Lin, Yijia Xie, Jiahong Xie, Yuehao Huang, Ruoyu Wang, Jiajun Lv, Yukai Ma, Xingxing Zuo

专题命中模仿学习与强化学习：robotics(abstract)；manipulation(abstract)；分类 cs.RO、cs.AI

2504.12609 2025-08-19 cs.RO cs.AI 73%

Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration

Tyler Ga Wei Lum, Olivia Y. Lee, C. Karen Liu, Jeannette Bohg

机构 * Stanford University（斯坦福大学）

专题命中模仿学习与强化学习：robot learning(abstract)；manipulation(abstract)；分类 cs.RO、cs.AI

2508.11049 2025-08-18 cs.RO cs.CV 73%

GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning

Kelin Yu, Sheng Zhang, Harshit Soora, Furong Huang, Heng Huang, Pratap Tokekar, Ruohan Gao

机构 * University of Maryland, College Park（马里兰大学 College Park分校）

专题命中模仿学习与强化学习：robot learning(abstract)；manipulation(abstract)；分类 cs.RO、cs.CV

Comments Published at ICCV 2025

2508.06108 2025-08-11 cs.LG cs.AI 73%

GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning

Xing Lei, Wenyan Yang, Kaiqiang Ke, Shentao Yang, Xuetao Zhang, Joni Pajarinen, Donglin Wang

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

2508.00106 2025-08-04 cs.AI cs.LG cs.LO cs.SY eess.SY 73%

Hyperproperty-Constrained Secure Reinforcement Learning

Ernest Bonnah, Luan Viet Nguyen, Khaza Anuarul Hoque

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

Comments Accepted in IEEE/ACM MEMOCODE 2025

2507.23391 2025-08-01 cs.LG cs.RO 73%

Policy Learning from Large Vision-Language Model Feedback without Reward Modeling

Tung M. Luu, Donghoon Lee, Younghwan Lee, Chang D. Yoo

机构 * School of Electrical Engineering, KAIST（韩国科学技术院电子工程学院）

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

Comments Accepted to IROS 2025

2304.04911 2025-07-30 cs.LG cs.RO cs.SY eess.SY 73%

Real-Time Model-Free Deep Reinforcement Learning for Force Control of a Series Elastic Actuator

Ruturaj Sambhus, Aydin Gokce, Stephen Welch, Connor W. Herron, Alexander Leonessa

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

Comments 8 pages, 5 figures, submitted to IROS 2023

Journal ref 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, USA, 2023

2504.01301 2025-07-29 cs.RO cs.AI 73%

Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers

Takumi Kobayashi, Masato Kobayashi, Thanpimon Buamanee, Yuki Uranishi

机构 * Graduate School of Information Science and Technology, The University of Osaka（信息科学与技术研究生学校，大阪大学）； D3 Center, The University of Osaka（大阪大学D3中心）； Graduate School of Maritime Sciences, Kobe University（海洋科学研究生学校， Kobe大学）

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

2507.16139 2025-07-23 cs.RO cs.LG 73%

Equivariant Goal Conditioned Contrastive Reinforcement Learning

Arsh Tangri, Nichols Crawford Taylor, Haojie Huang, Robert Platt

机构 * Khoury College of Computer Sciences Northeastern University（克劳利计算机科学学院东北大学）

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

2507.10174 2025-07-15 cs.AI cs.LG 73%

Should We Ever Prefer Decision Transformer for Offline Reinforcement Learning?

Yumi Omori, Zixuan Dong, Keith Ross

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

Comments Accepted by RLBrew: Ingredients for Developing Generalist Agents workshop (RLC 2025)

2310.04266 2025-07-11 cs.RO cs.AI 73%

DRIFT: Deep Reinforcement Learning for Intelligent Floating Platforms Trajectories

Matteo El-Hariry, Antoine Richard, Vivek Muralidharan, Matthieu Geist, Miguel Olivares-Mendez

机构 * Space Robotics (SpaceR) Research Group, SnT, University of Luxembourg（卢森堡大学空间机器人（SpaceR）研究组）； Cohere

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

Comments Updated to the version accepted at IROS 2024. Minor revisions based on peer review

2507.06628 2025-07-10 cs.LG cs.AI 73%

Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning

Jinmin He, Kai Li, Yifan Zang, Haobo Fu, Qiang Fu, Junliang Xing, Jian Cheng

机构 * C2DL, Institute of Automation, Chinese Academy of Sciences（C2DL，自动化研究所，中国科学院）； School of Artificial Intelligence, University of Chinese Academy of Sciences（人工智能学院，中国科学院大学）； Tencent AI Lab（腾讯AI实验室）； Tsinghua University（清华大学）

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

Comments ICML2025

Journal ref Proceedings of the 42nd International Conference on Machine Learning, Vancouver, Canada. PMLR 267, 2025

2501.05329 2025-07-04 cs.LG cs.RO 73%

Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task Learning

Dmytro Kuzmenko, Nadiya Shvai

机构 * National University of Kyiv-Mohyla Academy（基辅莫希拉大学）

专题命中模仿学习与强化学习：robotics(abstract)；world model(abstract)；分类 cs.RO、cs.LG

Comments Preprint of an extended abstract accepted to AAMAS 2025

Journal ref Proceedings of the 24th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2025), pp. 2597-2599, ACM, 2025

2507.01823 2025-07-03 cs.LG cs.RO 73%

TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning Agents

Dmytro Kuzmenko, Nadiya Shvai

机构 * Department of Multimedia Systems, NaUKMA（多媒体系统系，NaUKMA）； Department of Mathematics, NaUKMA（数学系，NaUKMA）

专题命中模仿学习与强化学习：robotics(abstract)；world model(abstract)；分类 cs.RO、cs.LG

Comments Preprint of a manuscript submitted for peer review

2506.23944 2025-07-02 cs.RO cs.AI 73%

Adapt Your Body: Mitigating Proprioception Shifts in Imitation Learning

Fuhang Kuang, Jiacheng You, Yingdong Hu, Tong Zhang, Chuan Wen, Yang Gao

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

Comments Need further modification

2505.19769 2025-06-25 cs.RO cs.AI 73%

TeViR: Text-to-Video Reward with Diffusion Models for Efficient Reinforcement Learning

Yuhui Chen, Haoran Li, Zhennan Jiang, Haowei Wen, Dongbin Zhao

机构 * Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）

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

2506.13583 2025-06-17 cs.HC cs.AI cs.RO 73%

Can you see how I learn? Human observers' inferences about Reinforcement Learning agents' learning processes

Bernhard Hilpert, Muhan Hou, Kim Baraka, Joost Broekens

机构 * Leiden University（莱顿大学）； Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）

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

2504.20969 2025-06-17 cs.RO cs.LG 73%

XPG-RL: Reinforcement Learning with Explainable Priority Guidance for Efficiency-Boosted Mechanical Search

Yiting Zhang, Shichen Li, Elena Shrestha

机构 * University of Michigan, Ann Arbor（密歇根大学）； University of Illinois, Urbana-Champaign（伊利诺伊大学）

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

Comments Accepted to RSS 2025 Workshop on Learned Robot Representations (RoboReps)

2505.17714 2025-05-26 cs.LG cs.AI cs.CL 73%

PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization

Ben Rahman

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

Comments This manuscript builds upon an earlier version posted to TechRxiv. This arXiv version includes an updated comparison with GRPO (Group Relative Policy Optimization)

2505.15143 2025-05-22 cs.LG cs.RO 73%

Filtering Learning Histories Enhances In-Context Reinforcement Learning

Weiqin Chen, Xinjie Zhang, Dharmashankar Subramanian, Santiago Paternain

机构 * Rensselaer Polytechnic Institute（拉特格斯理工学院）； Columbia University（哥伦比亚大学）； IBM Research（IBM研究院）

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

2410.20487 2025-05-20 cs.LG cs.AI 73%

Efficient Diversity-based Experience Replay for Deep Reinforcement Learning

Kaiyan Zhao, Yiming Wang, Yuyang Chen, Yan Li, Leong Hou U, Xiaoguang Niu

机构 * School of Computer Science, Wuhan University（武汉大学计算机学院）； State Key Laboratory of Internet of Things for Smart City, University of Macau（澳门大学智能城市物联网国家重点实验室）； School of Artificial Intelligence Shenzhen Polytechnic University（深圳职业技术学院人工智能学院）

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

2505.06079 2025-05-12 cs.RO cs.CV 73%

TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with Demonstrations

Shuaiyi Huang, Mara Levy, Anubhav Gupta, Daniel Ekpo, Ruijie Zheng, Abhinav Shrivastava

机构 * University of Maryland, College Park（马里兰大学学院公园分校）

专题命中模仿学习与强化学习：manipulation(abstract)；robotic(abstract)；分类 cs.RO、cs.CV

Comments ICRA 2025

2505.03172 2025-05-07 cs.LG cs.AI 73%

Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning

Caleb Chuck, Fan Feng, Carl Qi, Chang Shi, Siddhant Agarwal, Amy Zhang, Scott Niekum

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校）； University of California San Diego（加州大学圣地亚哥分校）； MBZUAI（马克斯·普朗克人工智能研究所）； University of Massachusetts Amherst（马萨诸塞大学阿姆赫斯特分校）

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

Comments Published at ICLR 2025

Journal ref The Thirteenth International Conference on Learning Representations. 2025

2504.20520 2025-04-30 cs.RO cs.AI 73%

PRISM: Projection-based Reward Integration for Scene-Aware Real-to-Sim-to-Real Transfer with Few Demonstrations

Haowen Sun, Han Wang, Chengzhong Ma, Shaolong Zhang, Jiawei Ye, Xingyu Chen, Xuguang Lan

机构 * National Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能国家级实验室）； Institute of Artificial Intelligence and Robotics（人工智能与机器人研究院）； Xi’an Jiaotong University（西安交通大学）

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

2504.16925 2025-04-24 cs.RO cs.AI 73%

Latent Diffusion Planning for Imitation Learning

Amber Xie, Oleh Rybkin, Dorsa Sadigh, Chelsea Finn

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

2504.15472 2025-04-23 cs.RO cs.LG cs.SY eess.SY 73%

LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning

Pingcheng Jian, Xiao Wei, Yanbaihui Liu, Samuel A. Moore, Michael M. Zavlanos, Boyuan Chen

专题命中模仿学习与强化学习：robot learning(abstract)；manipulation(abstract)；分类 cs.RO、cs.LG

2504.09242 2025-04-15 cs.RO cs.AI 73%

Development of a PPO-Reinforcement Learned Walking Tripedal Soft-Legged Robot using SOFA

Yomna Mokhtar, Tarek Shohdy, Abdallah A. Hassan, Mostafa Eshra, Omar Elmenawy, Osama Khalil, Haitham El-Hussieny

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

2503.17125 2025-03-31 cs.RO cs.AI 73%

LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning

Chan Kim, Seung-Woo Seo, Seong-Woo Kim

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

Comments 14 pages, 16 figures

2503.20139 2025-03-27 cs.LG cs.AI 73%

Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learning

Yongshuai Liu, Xin Liu

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

1. 模仿学习与强化学习 4111 篇

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models

SimGenHOI: Physically Realistic Whole-Body Humanoid-Object Interaction via Generative Modeling and Reinforcement Learning

Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration

GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning

GCHR : Goal-Conditioned Hindsight Regularization for Sample-Efficient Reinforcement Learning

Hyperproperty-Constrained Secure Reinforcement Learning

Policy Learning from Large Vision-Language Model Feedback without Reward Modeling

Real-Time Model-Free Deep Reinforcement Learning for Force Control of a Series Elastic Actuator

Bi-LAT: Bilateral Control-Based Imitation Learning via Natural Language and Action Chunking with Transformers

Equivariant Goal Conditioned Contrastive Reinforcement Learning

Should We Ever Prefer Decision Transformer for Offline Reinforcement Learning?

DRIFT: Deep Reinforcement Learning for Intelligent Floating Platforms Trajectories

Goal-Oriented Skill Abstraction for Offline Multi-Task Reinforcement Learning

Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task Learning

TD-MPC-Opt: Distilling Model-Based Multi-Task Reinforcement Learning Agents

Adapt Your Body: Mitigating Proprioception Shifts in Imitation Learning

TeViR: Text-to-Video Reward with Diffusion Models for Efficient Reinforcement Learning

Can you see how I learn? Human observers' inferences about Reinforcement Learning agents' learning processes

XPG-RL: Reinforcement Learning with Explainable Priority Guidance for Efficiency-Boosted Mechanical Search

PPO-BR: Dual-Signal Entropy-Reward Adaptation for Trust Region Policy Optimization

Filtering Learning Histories Enhances In-Context Reinforcement Learning

Efficient Diversity-based Experience Replay for Deep Reinforcement Learning

TREND: Tri-teaching for Robust Preference-based Reinforcement Learning with Demonstrations

Null Counterfactual Factor Interactions for Goal-Conditioned Reinforcement Learning

PRISM: Projection-based Reward Integration for Scene-Aware Real-to-Sim-to-Real Transfer with Few Demonstrations

Latent Diffusion Planning for Imitation Learning

LAPP: Large Language Model Feedback for Preference-Driven Reinforcement Learning

Development of a PPO-Reinforcement Learned Walking Tripedal Soft-Legged Robot using SOFA

LaMOuR: Leveraging Language Models for Out-of-Distribution Recovery in Reinforcement Learning

Look Before Leap: Look-Ahead Planning with Uncertainty in Reinforcement Learning