机器人 / 具身智能 - arXivDaily 专题

2006.09359 2021-04-27 cs.LG cs.RO stat.ML 79%

AWAC: Accelerating Online Reinforcement Learning with Offline Datasets

Ashvin Nair, Abhishek Gupta, Murtaza Dalal, Sergey Levine

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

Comments 17 pages. Website: https://awacrl.github.io/

1912.13414 2020-08-04 cs.LG cs.AI stat.ML 79%

Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards

Xingyu Lu, Stas Tiomkin, Pieter Abbeel

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

2004.14288 2020-07-16 cs.RO cs.LG cs.SY eess.SY 79%

Actor-Critic Reinforcement Learning for Control with Stability Guarantee

Minghao Han, Lixian Zhang, Jun Wang, Wei Pan

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

Comments IEEE RA-L + IROS 2020

2006.00900 2020-06-02 cs.LG cs.AI stat.ML 79%

PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals

Henry Charlesworth, Giovanni Montana

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

2003.12948 2020-05-26 cs.LG cs.AI 79%

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

Chongzhen Zhang, Jianrui Wang, Gary G. Yen, Chaoqiang Zhao, Qiyu Sun, Yang Tang, Feng Qian, Jürgen Kurths

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

1808.09105 2019-06-25 cs.LG cs.RO stat.ML 79%

SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning

Marvin Zhang, Sharad Vikram, Laura Smith, Pieter Abbeel, Matthew J. Johnson, Sergey Levine

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

Comments ICML 2019. Project website: https://sites.google.com/view/icml19solar

2509.13949 2026-03-18 cs.RO 78%

SHaRe-RL: Structured, Interactive Reinforcement Learning for Contact-Rich Industrial Assembly Tasks

SHaRe-RL：结构化、交互式强化学习用于接触密集型工业装配任务

Jannick Stranghöner, Philipp Hartmann, Marco Braun, Sebastian Wrede, Klaus Neumann

机构 * CITEC, Faculty of Technology, Bielefeld University, Germany（CITEC，技术学院，比勒菲尔德大学，德国）； Fraunhofer IOSB-INA, Lemgo, Germany（弗劳恩霍夫 IOSB-INA，莱姆戈，德国）

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

AI总结 SHaRe-RL通过整合先验知识，解决了工业装配中高混合低体积生产对精度、安全性和可靠性的需求，实现了高效安全的在线学习。

Comments 8 pages, 8 figures, accepted to IEEE International Conference on Robotics and Automation (ICRA) 2026

2210.15185 2023-05-24 cs.RO cs.AI cs.CV cs.LG 78%

SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering

Jun Lv, Yunhai Feng, Cheng Zhang, Shuang Zhao, Lin Shao, Cewu Lu

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

Comments Accepted to Robotics: Science and Systems (RSS) 2023

1810.03237 2018-10-09 cs.RO cs.AI cs.CV cs.LG 78%

Task-Embedded Control Networks for Few-Shot Imitation Learning

Stephen James, Michael Bloesch, Andrew J. Davison

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

Comments Published at the Conference on Robot Learning (CoRL) 2018

2606.24597 2026-06-24 cs.CL 新提交 78%

Qwen-AgentWorld: Language World Models for General Agents

Qwen-AgentWorld: 通用智能体的语言世界模型

Yuxin Zuo, Zikai Xiao, Li Sheng, Fei Huang, Jianhong Tu, Yuxuan Liu, Tianyi Tang, Xiaomeng Hu, Yang Su, Qingfeng Lan, Yantao Liu, Qin Zhu, Yinger Zhang, Bowen Yu, Haiquan Zhao, Haiyang Xu, Jianxin Yang, Jiayang Cheng, Junyang Wang, Lianghao Deng, Mingfeng Xue, Tianyi Bai, Yang Fan, Yubo Ma, Yucheng Li, Zeyu Cui, Zhihai Wang, Zhihui Xie, Zhuorui Ye, An Yang, Dayiheng Liu, Jingren Zhou, Ning Ding

机构 * Qwen Team（Qwen团队）

专题命中模仿学习与强化学习：world model(title,abstract)

AI总结提出基于语言模型的世界模型Qwen-AgentWorld，通过三阶段训练（CPT、SFT、RL）模拟7个领域的智能体环境，并构建AgentWorldBench基准，实验表明其显著优于现有模型，且能作为环境模拟器和智能体基础模型提升下游性能。

2510.12560 2026-06-16 cs.CV cs.LG cs.RO 版本更新 78%

CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving

CoIRL-AD：面向自动驾驶的潜在世界模型中的协作-竞争模仿-强化学习

Xiaoji Zheng, Ziyuan Yang, Yanhao Chen, Yuhang Peng, Yuanrong Tang, Gengyuan Liu, Bokui Chen, Jiangtao Gong

机构 * University of Science and Technology of China（中国科学技术大学）； Tsinghua University（清华大学）

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

AI总结提出CoIRL-AD框架，通过解耦模仿学习与强化学习、利用潜在世界模型进行长时程奖励估计以及引入竞争机制，在离线训练中提升自动驾驶的鲁棒性，尤其在跨城市泛化和长尾场景中表现优异。

Comments 19 pages, 22 figures, ICML 2026

2606.14674 2026-06-15 cs.CL 新提交 78%

AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition

AgentSpec: 通过受控组合理解具身智能体脚手架

Jixuan Chen, Jianzhi Shen, Haoqiang Kang, Zhi Hong, Qingyi Jiang, Soham Bose, Yiming Zhang, Leon Leng, Amit Vyas, Lingjun Mao, Siru Ouyang, Kun Zhou, Lianhui Qin

机构 * University of California, San Diego（加利福尼亚大学圣迭戈分校）； Johns Hopkins University（约翰霍普金斯大学）； University of Washington（华盛顿大学）； University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

专题命中模仿学习与强化学习：embodied agent(title,abstract)

AI总结提出AgentSpec模块化规范框架，将具身智能体表示为可复用策略组件的类型化组合，通过标准化接口实现受控组件替换与重组，揭示脚手架兼容性和交互效应对性能的主导作用。

1904.09865 2026-06-04 eess.SY cs.SY 78%

Adaptive Guidance and Integrated Navigation with Reinforcement Meta-Learning

自适应引导与集成导航的强化元学习

Brian Gaudet, Richard Linares, Roberto Furfaro

专题命中模仿学习与强化学习：navigation(title,abstract)

AI总结本文提出了一种基于强化元学习的自适应引导系统，采用递归策略和价值函数近似器，通过递归网络层使部署策略能实时适应作用在智能体上的环境力，在四个具有未知但高度动态变化的挑战性环境中比较了DR/DV引导律、非递归策略的RL代理和递归策略的RL代理的性能，并展示了RL元学习优化的策略在火星着陆环境中仅使用多普勒雷达高度计读数，在小行星着陆环境中仅使用LIDAR高度计读数时实现引导和导航的整合能力。

Comments arXiv admin note: substantial text overlap with arXiv:1901.04473

2602.05051 2026-02-06 cs.LG cs.AI cs.RO 78%

ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation

ReFORM：通过噪声操控实现支持下的离线强化学习

Songyuan Zhang, Oswin So, H. M. Sabbir Ahmad, Eric Yang Yu, Matthew Cleaveland, Mitchell Black, Chuchu Fan

机构 * MIT（麻省理工学院）； Boston University（波士顿大学）； MIT Lincoln Laboratory（麻省理工学院林伍德实验室）

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

AI总结 ReFORM通过反射流策略和噪声操控，在离线强化学习中实现更宽松的支持约束，从而在多模态分布下提升策略性能。

Comments 24 pages, 17 figures; Accepted by the fourteenth International Conference on Learning Representations (ICLR 2026)

2509.22628 2025-10-01 cs.CV cs.AI cs.LG 78%

UML-CoT: Structured Reasoning and Planning with Unified Modeling Language for Robotic Room Cleaning

Hongyu Chen, Guangrun Wang

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

2509.24219 2025-09-30 cs.RO cs.AI cs.LG 78%

ViReSkill: Vision-Grounded Replanning with Skill Memory for LLM-Based Planning in Lifelong Robot Learning

Tomoyuki Kagaya, Subramanian Lakshmi, Anbang Ye, Thong Jing Yuan, Jayashree Karlekar, Sugiri Pranata, Natsuki Murakami, Akira Kinose, Yang You

机构 * Panasonic Connect Co., Ltd.（松下电器（株式会社））； Panasonic R&D Center（松下研发中心）； National University of Singapore（新加坡国立大学）

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

2501.01141 2025-01-03 cs.NI 78%

Embodied AI-Enhanced Vehicular Networks: An Integrated Large Language Models and Reinforcement Learning Method

Ruichen Zhang, Changyuan Zhao, Hongyang Du, Dusit Niyato, Jiacheng Wang, Suttinee Sawadsitang, Xuemin Shen, Dong In Kim

专题命中模仿学习与强化学习：embodied AI(title,abstract)

Comments 14 pages, 10 figures

2410.15205 2024-10-22 cs.MA 78%

DTPPO: Dual-Transformer Encoder-based Proximal Policy Optimization for Multi-UAV Navigation in Unseen Complex Environments

Anning Wei, Jintao Liang, Kaiyuan Lin, Ziyue Li, Rui Zhao

专题命中模仿学习与强化学习：navigation(title,abstract)

2408.05781 2024-09-04 cs.LG cs.AI cs.CV 78%

CURLing the Dream: Contrastive Representations for World Modeling in Reinforcement Learning

Victor Augusto Kich, Jair Augusto Bottega, Raul Steinmetz, Ricardo Bedin Grando, Ayano Yorozu, Akihisa Ohya

专题命中模仿学习与强化学习：world model(title)；分类 cs.AI、cs.CV、cs.LG

Comments Paper accepted for 24th International Conference on Control, Automation and Systems (ICCAS)

2212.11498 2024-09-02 cs.LG cs.AI cs.MA cs.RO 78%

Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers

Aleksandar Krnjaic, Raul D. Steleac, Jonathan D. Thomas, Georgios Papoudakis, Lukas Schäfer, Andrew Wing Keung To, Kuan-Ho Lao, Murat Cubuktepe, Matthew Haley, Peter Börsting, Stefano V. Albrecht

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

Comments IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024

2110.15237 2024-06-10 eess.SY cs.SY 78%

Data Informed Residual Reinforcement Learning for High-Dimensional Robotic Tracking Control

Cong Li, Fangzhou Liu, Yongchao Wang, Martin Buss

专题命中模仿学习与强化学习：robotic(title,abstract)

2310.08595 2023-10-17 cs.RO cs.AI cs.LG 78%

Deep Reinforcement Learning for Autonomous Vehicle Intersection Navigation

Badr Ben Elallid, Hamza El Alaoui, Nabil Benamar

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

Comments Accepted for publication in the 2023 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT)

2301.00051 2023-10-16 cs.LG cs.AI cs.RO 78%

Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary Tasks

Trevor Ablett, Bryan Chan, Jonathan Kelly

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

Comments In IEEE Robotics and Automation Letters (RA-L) and presented at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'23), Detroit, MI, USA, Oct. 1-5, 2023. arXiv admin note: substantial text overlap with arXiv:2112.08932

Journal ref IEEE Robotics and Automation Letters (RA-L), Vol. 8, No. 3, pp. 1263-1270, Jan. 2023

2302.12617 2023-02-27 cs.RO cs.AI cs.LG 78%

Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains

Jingwei Zhang, Jost Tobias Springenberg, Arunkumar Byravan, Leonard Hasenclever, Abbas Abdolmaleki, Dushyant Rao, Nicolas Heess, Martin Riedmiller

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

2210.10865 2022-10-21 cs.RO cs.AI cs.LG cs.SY eess.SY 78%

Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization

Thomas Lew, Sumeet Singh, Mario Prats, Jeffrey Bingham, Jonathan Weisz, Benjie Holson, Xiaohan Zhang, Vikas Sindhwani, Yao Lu, Fei Xia, Peng Xu, Tingnan Zhang, Jie Tan, Montserrat Gonzalez

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

2210.02891 2022-10-07 cs.RO cs.AI cs.LG 78%

Transferring Knowledge for Reinforcement Learning in Contact-Rich Manipulation

Quantao Yang, Johannes A. Stork, Todor Stoyanov

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

2009.12068 2021-05-25 cs.AI cs.LG cs.RO 78%

Deep Reinforcement Learning with a Stage Incentive Mechanism of Dense Reward for Robotic Trajectory Planning

Gang Peng, Jin Yang, Xinde Lia, Mohammad Omar Khyam

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

2001.11710 2020-11-16 cs.MA 78%

Context-Aware Deep Q-Network for Decentralized Cooperative Reconnaissance by a Robotic Swarm

Nishant Mohanty, Mohitvishnu S. Gadde, Suresh Sundaram, Narasimhan Sundararajan, P. B. Sujit

专题命中模仿学习与强化学习：robotic(title,abstract)

Comments "For associated video file, refer to http://bit.ly/cadqnvideo"

2011.01046 2020-11-03 cs.RO cs.AI cs.LG 78%

NEARL: Non-Explicit Action Reinforcement Learning for Robotic Control

Nan Lin, Yuxuan Li, Yujun Zhu, Ruolin Wang, Xiayu Zhang, Jianmin Ji, Keke Tang, Xiaoping Chen, Xinming Zhang

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

1909.10707 2020-08-27 cs.RO cs.AI cs.LG 78%

Invariant Transform Experience Replay: Data Augmentation for Deep Reinforcement Learning

Yijiong Lin, Jiancong Huang, Matthieu Zimmer, Yisheng Guan, Juan Rojas, Paul Weng

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

Comments 8 pages, 11 figures, additional 3 pages for appendix. IEEE Robotics and Automation Letters (RAL), 2020. Also in: Intelligent Robots and Systems (IROS)

Journal ref IEEE Robotics and Automation Letters, Volume: 5, Issue: 4, p. 6615-6622, Oct. 2020

1. 模仿学习与强化学习 4106 篇

AWAC: Accelerating Online Reinforcement Learning with Offline Datasets

Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards

Actor-Critic Reinforcement Learning for Control with Stability Guarantee

PlanGAN: Model-based Planning With Sparse Rewards and Multiple Goals

When Autonomous Systems Meet Accuracy and Transferability through AI: A Survey

SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning

SHaRe-RL: Structured, Interactive Reinforcement Learning for Contact-Rich Industrial Assembly Tasks

SAM-RL: Sensing-Aware Model-Based Reinforcement Learning via Differentiable Physics-Based Simulation and Rendering

Task-Embedded Control Networks for Few-Shot Imitation Learning

Qwen-AgentWorld: Language World Models for General Agents

CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving

AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Composition

Adaptive Guidance and Integrated Navigation with Reinforcement Meta-Learning

ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation

UML-CoT: Structured Reasoning and Planning with Unified Modeling Language for Robotic Room Cleaning

ViReSkill: Vision-Grounded Replanning with Skill Memory for LLM-Based Planning in Lifelong Robot Learning

Embodied AI-Enhanced Vehicular Networks: An Integrated Large Language Models and Reinforcement Learning Method

DTPPO: Dual-Transformer Encoder-based Proximal Policy Optimization for Multi-UAV Navigation in Unseen Complex Environments

CURLing the Dream: Contrastive Representations for World Modeling in Reinforcement Learning

Scalable Multi-Agent Reinforcement Learning for Warehouse Logistics with Robotic and Human Co-Workers

Data Informed Residual Reinforcement Learning for High-Dimensional Robotic Tracking Control

Deep Reinforcement Learning for Autonomous Vehicle Intersection Navigation

Learning from Guided Play: Improving Exploration for Adversarial Imitation Learning with Simple Auxiliary Tasks

Leveraging Jumpy Models for Planning and Fast Learning in Robotic Domains

Robotic Table Wiping via Reinforcement Learning and Whole-body Trajectory Optimization

Transferring Knowledge for Reinforcement Learning in Contact-Rich Manipulation

Deep Reinforcement Learning with a Stage Incentive Mechanism of Dense Reward for Robotic Trajectory Planning

Context-Aware Deep Q-Network for Decentralized Cooperative Reconnaissance by a Robotic Swarm

NEARL: Non-Explicit Action Reinforcement Learning for Robotic Control

Invariant Transform Experience Replay: Data Augmentation for Deep Reinforcement Learning