机器人 / 具身智能 - arXivDaily 专题

1511.04156 2016-09-28 stat.ML cs.LG q-bio.NC 57%

Neuroprosthetic decoder training as imitation learning

Josh Merel, David Carlson, Liam Paninski, John P. Cunningham

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

1606.09152 2016-08-23 cs.LG 57%

Actor-critic versus direct policy search: a comparison based on sample complexity

Arnaud de Froissard de Broissia, Olivier Sigaud

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

Comments Proceedings JFPDA (Journees Francaises Planification Decision Apprentissage)

1608.04996 2016-08-18 cs.AI 57%

Open Problem: Approximate Planning of POMDPs in the class of Memoryless Policies

Kamyar Azizzadenesheli, Alessandro Lazaric, Animashree Anandkumar

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

Comments arXiv admin note: substantial text overlap with arXiv:1602.07764

Journal ref 29th Annual Conference on Learning Theory (2016) 1639--1642

1509.08455 2015-09-29 stat.ML cs.LG 57%

Efficient Empowerment

Maximilian Karl, Justin Bayer, Patrick van der Smagt

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

1409.7552 2015-09-17 stat.ML cs.LG 57%

The Advantage of Cross Entropy over Entropy in Iterative Information Gathering

Johannes Kulick, Robert Lieck, Marc Toussaint

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

Comments 24 pages

1506.02080 2015-06-09 cs.LG stat.ML 57%

Local Nonstationarity for Efficient Bayesian Optimization

Ruben Martinez-Cantin

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

1410.8233 2014-10-31 cs.AI 57%

Do Artificial Reinforcement-Learning Agents Matter Morally?

Brian Tomasik

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

Comments 37 pages

1303.2651 2014-04-01 cs.LG cs.IR 57%

Hybrid Q-Learning Applied to Ubiquitous recommender system

Djallel Bouneffouf

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

Comments arXiv admin note: substantial text overlap with arXiv:1301.4351, arXiv:1303.2308

1303.7201 2013-03-29 cs.AI 57%

Design for a Darwinian Brain: Part 2. Cognitive Architecture

Chrisantha Fernando, Vera Vasas

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

Comments Submitted as Part 2 to Living Machines 2013, Natural History Museum, London. Code available on github as it is being developed to implement the cognitive architecture above, here... https://github.com/ctf20/DarwinianNeurodynamics

1301.3630 2013-03-22 cs.LG 57%

Behavior Pattern Recognition using A New Representation Model

Qifeng Qiao, Peter A. Beling

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

1303.3679 2013-03-18 cs.RO 57%

Minimum-violation LTL Planning with Conflicting Specifications

Jana Tumova, Luis I. Reyes Castro, Sertac Karaman, Emilio Frazzoli, Daniela Rus

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

Comments extended version of the ACC 2013 paper

1208.0984 2012-08-07 cs.LG 57%

APRIL: Active Preference-learning based Reinforcement Learning

Riad Akrour, Marc Schoenauer, Michèle Sebag

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

Journal ref ECML PKDD 2012 7524 (2012) 116-131

2607.13579 2026-07-16 cs.RO cs.AI cs.LG 新提交 56%

Agile perceptive multi-skill locomotion for quadrupedal robots in the wild

野外四足机器人的敏捷感知多技能运动

Jun-Gill Kang, Jaehyun Park, Tae-Gyu Song, Joon-Ha Kim, Seungwoo Hong, Hae-Won Park

机构 * Agency for Defense Development（国防发展局）； Korea Advanced Institute of Science and Technology（韩国科学技术院）； DIDEN Robotics（迪登机器人公司）； Korea University（韩国大学）

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

AI总结研究使四足机器人在复杂地形实现多技能运动的问题，提出 APT-RL 框架，利用机载感知和计算自主转换技能，通过轨迹优化生成数据集训练技能，经实验验证该框架能让机器人在复杂环境敏捷机动，稳健穿越多样障碍物。

Comments Project page: https://skillquadsr.github.io/ ,This is the author's version of the work. It is posted here by permission of the AAAS for personal use, not for redistribution. The definitive version was published in Science Robotics on 7.15.2026; doi: 10.1126/scirobotics.adz7397. Jun-Gill Kang and Jaehyun Park are co-first authors. Seungwoo Hong and Hae-Won Park are co-corresponding authors

2312.09436 2026-04-13 cs.RO cs.AI cs.LG cs.SY eess.SY 56%

Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy

基于粗粒度建议自主性的交通优化时序迁移学习

Jung-Hoon Cho, Sirui Li, Jeongyun Kim, Cathy Wu

机构 * Department of Civil and Environmental Engineering, Massachusetts Institute of Technology（麻省理工学院土木与环境工程系）； Laboratory for Information & Decision Systems, Massachusetts Institute of Technology（麻省理工学院信息与决策系统实验室）； Department of Mechanical and Automotive Engineering, Seoul National University of Science and Technology（首尔科学技术大学机械与汽车工程系）

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

AI总结本文提出时序迁移学习算法，通过零样本迁移解决自动驾驶中的粗粒度建议任务，验证了其在混合交通场景中的有效性。

Comments 18 pages, 12 figures

Journal ref IEEE Transactions on Robotics, 2026

1909.07299 2026-04-07 cs.RO cs.AI cs.LG 56%

Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning

基于线性时序逻辑规范的控制合成使用无模型强化学习

Alper Kamil Bozkurt, Yu Wang, Michael M. Zavlanos, Miroslav Pajic

机构 * Duke University（杜克大学）

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

AI总结本文提出一种强化学习框架，用于在未知随机环境中基于线性时序逻辑规范合成控制策略，通过无模型强化学习最大化满足LTL公式概率，确保算法收敛至最优策略。

Journal ref 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France, 2020, pp. 10349-10355

2603.20230 2026-03-24 cs.RO cs.AI cs.LG 56%

Beyond Scalar Rewards: Distributional Reinforcement Learning with Preordered Objectives for Safe and Reliable Autonomous Driving

超越标量奖励：用于安全可靠自动驾驶的预序目标分布强化学习

Ahmed Abouelazm, Jonas Michel, Daniel Bogdoll, Philip Schörner, J. Marius Zöllner

机构 * FZI Research Center for Information Technology（弗劳恩霍夫研究所信息技术研究中心）； Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）

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

AI总结本文提出预序多目标MDP框架，通过引入量化主导指标提升自动驾驶安全性和可靠性，实验表明其在Carla中表现出更优的性能和更稳健的策略。

Comments First and Second authors contributed equally; Accepted to the 2026 IEEE International Conference on Robotics and Automation (ICRA 2026)

2602.05091 2026-02-06 cs.AI cs.LG cs.RO physics.space-ph 56%

Evaluating Robustness and Adaptability in Learning-Based Mission Planning for Active Debris Removal

评估基于学习的任务规划在主动清除任务中的鲁棒性和适应性

Agni Bandyopadhyay, Günther Waxenegger-Wilfing

机构 * Faculty of Mathematics and Computer Science, Julius-Maximilians-Universität Würzburg（数学与计算机科学学院，维尔堡大学）

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

AI总结本文评估了基于学习的任务规划在主动清除任务中的鲁棒性和适应性，比较了三种规划器在不同约束条件下的性能，发现领域随机化PPO在适应性上表现更优，而MCTS在处理约束变化时更稳定但计算成本高。

Comments Presented at Conference: International Conference on Space Robotics (ISPARO,2025) At: Sendai,Japan

2512.21063 2025-12-25 eess.SY cs.SY 56%

LSTM-Based Modeling and Reinforcement Learning Control of a Magnetically Actuated Catheter

基于LSTM的磁致动导管建模与强化学习控制

Arya Rashidinejad Meibodi, Mahbod Gholamali Sinaki, Khalil Alipour

专题命中模仿学习与强化学习：navigation(abstract)；robotics(comments)

AI总结本研究利用LSTM建模磁性导管系统，并通过强化学习控制其路径跟随，actor-critic控制器在精度和性能上优于DQN。

Comments Presented at the 13th RSI International Conference on Robotics and Mechatronics (ICRoM 2025), Dec. 16-18, 2025, Tehran, Iran

2511.22415 2025-12-01 cs.CR 56%

Exposing Vulnerabilities in RL: A Novel Stealthy Backdoor Attack through Reward Poisoning

揭示强化学习中的漏洞：通过奖励污染的新型隐秘后门攻击

Bokang Zhang, Chaojun Lu, Jianhui Li, Junfeng Wu

专题命中模仿学习与强化学习：manipulation(abstract)；robot learning(comments)

AI总结本文提出通过奖励污染对强化学习代理进行隐秘后门攻击，展示了在不同环境中攻击的有效性和隐蔽性。

Comments Workshop on Safe and Robust Robot Learning for Operation in the Real World at CoRL 2025

2505.21851 2025-09-26 cs.RO cs.AI cs.LG 56%

Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories

Sunshine Jiang, Xiaolin Fang, Nicholas Roy, Tomás Lozano-Pérez, Leslie Pack Kaelbling, Siddharth Ancha

机构 * Massachusetts Institute of Technology（麻省理工学院）

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

Comments Conference on Robot Learning (CoRL) 2025

2504.17838 2025-08-22 cs.LG cs.AI cs.RO 56%

CaRL: Learning Scalable Planning Policies with Simple Rewards

Bernhard Jaeger, Daniel Dauner, Jens Beißwenger, Simon Gerstenecker, Kashyap Chitta, Andreas Geiger

机构 * University of Tübingen（图宾根大学）； Tübingen AI Center（图宾根人工智能中心）； NVIDIA Research（NVIDIA研究）

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

Comments Accepted at the Conference on Robot Learning 2025

2506.14287 2025-06-18 cs.RO cs.AI cs.HC cs.LG 56%

Steering Robots with Inference-Time Interactions

Yanwei Wang

机构 * Department of Electrical Engineering and Computer Science（电气工程与计算机科学系）

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

Comments MIT Robotics PhD Thesis

2409.13867 2025-04-29 cs.RO cs.AI cs.LG cs.SY eess.SY 56%

MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safety

Justin Wang, Haimin Hu, Duy Phuong Nguyen, Jaime Fernández Fisac

机构 * Department of Electrical and Computer Engineering, Princeton University, USA（电气与计算机工程系，普林斯顿大学）

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

Comments Algorithmic Foundations of Robotics (WAFR) XVI

2504.18160 2025-04-28 cs.LG cs.AI cs.RO 56%

Offline Learning of Controllable Diverse Behaviors

Mathieu Petitbois, Rémy Portelas, Sylvain Lamprier, Ludovic Denoyer

机构 * Ubisoft La Forge（育碧La Forge）； University of Angers（昂西大学）； H Company（H公司）

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

Comments Generative Models for Robot Learning Workshop at ICLR 2025

2403.12203 2024-11-13 cs.RO cs.CV cs.LG 56%

Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight

Jiaxu Xing, Angel Romero, Leonard Bauersfeld, Davide Scaramuzza

机构 * University of Zurich（苏黎世大学）； Robotics and Perception Group（机器人与感知组）

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

Comments 8th Annual Conference on Robot Learning (CoRL)

2409.16882 2024-09-26 cs.LG cs.AI cs.RO 56%

Revisiting Space Mission Planning: A Reinforcement Learning-Guided Approach for Multi-Debris Rendezvous

Agni Bandyopadhyay, Guenther Waxenegger-Wilfing

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

Comments Accepted for publication at the 2024 International Conference on Space Robotics (iSpaRo)

2406.08805 2024-09-23 cs.LG cs.AI cs.RO 56%

A Dual Approach to Imitation Learning from Observations with Offline Datasets

Harshit Sikchi, Caleb Chuck, Amy Zhang, Scott Niekum

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

Comments 8th Conference on Robot Learning (CoRL 2024), Munich, Germany. 23 pages

2404.05695 2024-05-21 cs.RO cs.AI cs.LG cs.SY eess.SY 56%

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer

Xinyang Gu, Yen-Jen Wang, Jianyu Chen

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

Journal ref ICRA 2024 Workshop on Agile Robotics

2306.10216 2024-05-02 cs.LG cs.AI cs.RO 56%

Vanishing Bias Heuristic-guided Reinforcement Learning Algorithm

Qinru Li, Hao Xiang

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

Comments Robotics;Reinforcement Learning;

2311.13081 2024-04-10 cs.RO cs.AI cs.LG cs.SY eess.SY 56%

Learning to Fly in Seconds

Jonas Eschmann, Dario Albani, Giuseppe Loianno

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

Comments Accepted for publication in IEEE Robotics and Automation Letters (RA-L)

1. 模仿学习与强化学习 4134 篇

Neuroprosthetic decoder training as imitation learning

Actor-critic versus direct policy search: a comparison based on sample complexity

Open Problem: Approximate Planning of POMDPs in the class of Memoryless Policies

Efficient Empowerment

The Advantage of Cross Entropy over Entropy in Iterative Information Gathering

Local Nonstationarity for Efficient Bayesian Optimization

Do Artificial Reinforcement-Learning Agents Matter Morally?

Hybrid Q-Learning Applied to Ubiquitous recommender system

Design for a Darwinian Brain: Part 2. Cognitive Architecture

Behavior Pattern Recognition using A New Representation Model

Minimum-violation LTL Planning with Conflicting Specifications

APRIL: Active Preference-learning based Reinforcement Learning

Agile perceptive multi-skill locomotion for quadrupedal robots in the wild

Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy

Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning

Beyond Scalar Rewards: Distributional Reinforcement Learning with Preordered Objectives for Safe and Reliable Autonomous Driving

Evaluating Robustness and Adaptability in Learning-Based Mission Planning for Active Debris Removal

LSTM-Based Modeling and Reinforcement Learning Control of a Magnetically Actuated Catheter

Exposing Vulnerabilities in RL: A Novel Stealthy Backdoor Attack through Reward Poisoning

Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories

CaRL: Learning Scalable Planning Policies with Simple Rewards

Steering Robots with Inference-Time Interactions

MAGICS: Adversarial RL with Minimax Actors Guided by Implicit Critic Stackelberg for Convergent Neural Synthesis of Robot Safety

Offline Learning of Controllable Diverse Behaviors

Bootstrapping Reinforcement Learning with Imitation for Vision-Based Agile Flight

Revisiting Space Mission Planning: A Reinforcement Learning-Guided Approach for Multi-Debris Rendezvous

A Dual Approach to Imitation Learning from Observations with Offline Datasets

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer

Vanishing Bias Heuristic-guided Reinforcement Learning Algorithm

Learning to Fly in Seconds