机器人 / 具身智能 - arXivDaily 专题

2107.08170 2021-07-22 cs.LG cs.AI 81%

Megaverse: Simulating Embodied Agents at One Million Experiences per Second

Aleksei Petrenko, Erik Wijmans, Brennan Shacklett, Vladlen Koltun

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

Comments Paper published in ICML2021

2105.09719 2021-05-21 cs.AI cs.RO 81%

Towards a Sample Efficient Reinforcement Learning Pipeline for Vision Based Robotics

Maxence Mahe, Pierre Belamri, Jesus Bujalance Martin

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

Comments 10 Pages, 15 Figures, 1 Table

2105.07348 2021-05-18 cs.RO cs.AI 81%

Explainable Hierarchical Imitation Learning for Robotic Drink Pouring

Dandan Zhang, Yu Zheng, Qiang Li, Lei Wei, Dongsheng Zhang, Zhengyou Zhang

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

Comments 15 pages, 12 figures

2105.01006 2021-05-04 cs.RO cs.LG 81%

Robotic Surgery With Lean Reinforcement Learning

Yotam Barnoy, Molly O'Brien, Will Wang, Gregory Hager

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

2104.08212 2021-04-29 cs.RO cs.LG 81%

MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale

Dmitry Kalashnikov, Jacob Varley, Yevgen Chebotar, Benjamin Swanson, Rico Jonschkowski, Chelsea Finn, Sergey Levine, Karol Hausman

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

2103.03697 2021-03-08 cs.RO cs.AI 81%

Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms

Ali Ghadirzadeh, Xi Chen, Petra Poklukar, Chelsea Finn, Mårten Björkman, Danica Kragic

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

2103.03662 2021-03-08 cs.RO cs.AI cs.MA 81%

MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models

Daniël Willemsen, Mario Coppola, Guido C. H. E. de Croon

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

Comments Submitted to 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)

2101.06248 2021-03-03 cs.RO cs.AI 81%

Local Navigation and Docking of an Autonomous Robot Mower using Reinforcement Learning and Computer Vision

Ali Taghibakhshi, Nathan Ogden, Matthew West

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

2009.09689 2021-02-12 cs.RO cs.AI 81%

Reinforcement Learning Approaches in Social Robotics

Neziha Akalin, Amy Loutfi

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

2102.02376 2021-02-08 cs.RO cs.AI 81%

A review of motion planning algorithms for intelligent robotics

Chengmin Zhou, Bingding Huang, Pasi Fränti

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

Comments 38 pages

2012.14842 2021-01-01 cs.AI cs.RO 81%

Modeling Social Interaction for Baby in Simulated Environment for Developmental Robotics

Md Ashaduzzaman Rubel Mondol, Aishwarya Pothula, Deokgun Park

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

Comments 5 pages ( Including 1 page reference), 3 figures, Presented at BabyMind workshop, NIPS 2020

2012.11643 2020-12-23 cs.RO cs.AI 81%

myGym: Modular Toolkit for Visuomotor Robotic Tasks

Michal Vavrecka, Nikita Sokovnin, Megi Mejdrechova, Gabriela Sejnova, Marek Otahal

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

Comments 6 pages, 5 figures

2011.04764 2020-11-19 cs.LG cs.CV 81%

Deep Reinforcement Learning for Navigation in AAA Video Games

Eloi Alonso, Maxim Peter, David Goumard, Joshua Romoff

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

Comments Accepted to the NeurIPS 2020 Challenges of Real-World RL workshop

2004.14404 2020-05-26 cs.LG cs.RO 81%

Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks

Gerrit Schoettler, Ashvin Nair, Juan Aparicio Ojea, Sergey Levine, Eugen Solowjow

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

Comments 9 pages, 8 figures

1907.08591 2020-01-08 nlin.CD cs.AI cs.LG cs.SY eess.SY physics.flu-dyn 81%

Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning

Luca Biferale, Fabio Bonaccorso, Michele Buzzicotti, Patricio Clark Di Leoni, Kristian Gustavsson

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

1912.05205 2019-12-12 cs.RO cs.AI 81%

Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning

Tianying Wang, Hao Zhang, Wei Qi Toh, Hongyuan Zhu, Cheston Tan, Yan Wu, Yong Liu, Wei Jing

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

Comments Accepted by ROBIO 2019

1908.08659 2019-08-26 cs.RO cs.LG 81%

A Comparison of Action Spaces for Learning Manipulation Tasks

Patrick Varin, Lev Grossman, Scott Kuindersma

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

Comments Accepted as a conference paper at IROS 2019

1905.06274 2019-05-16 cs.LG cs.RO stat.ML 81%

Reinforcement Learning for Robotics and Control with Active Uncertainty Reduction

Narendra Patwardhan, Zequn Wang

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

1611.01652 2018-11-27 cs.NE cs.AI cs.RO 81%

A Differentiable Physics Engine for Deep Learning in Robotics

Jonas Degrave, Michiel Hermans, Joni Dambre, Francis wyffels

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

Comments Submitted for International Conference on Learning Representations 2017

1810.06746 2018-10-17 cs.LG cs.RO stat.ML 81%

Using Deep Reinforcement Learning for the Continuous Control of Robotic Arms

Winfried Lötzsch

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

1802.10264 2018-03-30 cs.RO cs.LG stat.ML 81%

Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods

Deirdre Quillen, Eric Jang, Ofir Nachum, Chelsea Finn, Julian Ibarz, Sergey Levine

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

Comments 8 pages

1606.06979 2016-06-23 cs.HC cs.AI cs.RO 81%

Simultaneous Control and Human Feedback in the Training of a Robotic Agent with Actor-Critic Reinforcement Learning

Kory W. Mathewson, Patrick M. Pilarski

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

Comments 7 pages, 3 figures, Accepted at the Interactive Machine Learning Workshop at IJCAI 2016 (IML): Connecting Humans and Machines

1605.09735 2016-06-01 cs.AI cs.RO math.OC stat.ML 81%

Information Theoretically Aided Reinforcement Learning for Embodied Agents

Guido Montufar, Keyan Ghazi-Zahedi, Nihat Ay

专题命中模仿学习与强化学习：embodied agent(title,abstract)；分类 cs.RO、cs.AI

Comments 10 pages, 4 figures, 8 pages appendix

1511.09249 2015-12-01 cs.AI cs.LG cs.NE 81%

On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models

Juergen Schmidhuber

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

Comments 36 pages, 1 figure. arXiv admin note: substantial text overlap with arXiv:1404.7828

2602.01266 2026-02-03 cs.RO 80%

Reinforcement Learning for Active Perception in Autonomous Navigation

自主导航中的主动感知强化学习

Grzegorz Malczyk, Mihir Kulkarni, Kostas Alexis

机构 * Department of Engineering Cybernetics, Norwegian University of Science and Technology (NTNU)（工程 cybernetics 系，挪威科学技术大学）

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

AI总结本文提出一种端到端强化学习框架，使无人机在复杂环境中通过主动控制相机实现安全导航与探索。

Comments Accepted to the IEEE International Conference on Robotics and Automation (ICRA) 2026

2511.17869 2025-11-25 cs.LG 80%

The Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems

霍克鲁斯：用于检测和缓解具身AI系统中奖励黑客行为的可解释任务分解

Subramanyam Sahoo, Jared Junkin

机构 * Berkeley AI Safety Initiative (BASIS) UC Berkeley（伯克利人工智能安全计划（BASIS）伯克利大学）； Department of Electrical and Computer Engineering Johns Hopkins University（电气与计算机工程系约翰霍普金斯大学）

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

AI总结本研究提出MITD方法，通过可解释性任务分解有效检测和缓解具身AI系统中的奖励黑客行为，实验表明分解深度可显著降低奖励黑客频率。

Comments Accepted to the NeurIPS (Mexico City) 2025 Workshop on Embodied and Safe-Assured Robotic Systems (E-SARS). Thanks to Aman Chadha

2506.10790 2025-06-13 cs.CV 80%

Human-Robot Navigation using Event-based Cameras and Reinforcement Learning

Ignacio Bugueno-Cordova, Javier Ruiz-del-Solar, Rodrigo Verschae

机构 * Department of Electrical Engineering, Universidad de Chile（智利大学电气工程系）； Advanced Mining Technology Center (AMTC), Universidad de Chile（智利大学先进采矿技术中心）； Institute of Engineering Sciences, Universidad de O’Higgins（奥希金斯大学工程科学研究所）

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

Comments https://ibugueno.github.io/hr-navigation-using-event-cameras-and-rl/

Journal ref 2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW); Fifth International Workshop on Event-Based Vision

2410.16591 2025-03-21 cs.RO 80%

Cycloidal Quasi-Direct Drive Actuator Designs with Learning-based Torque Estimation for Legged Robotics

Alvin Zhu, Yusuke Tanaka, Fadi Rafeedi, Dennis Hong

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

Comments Proceeding to 2025 IEEE International Conference on Robotics and Automation (ICRA25)

2503.08492 2025-03-12 cs.RO 80%

Hybrid Deep Reinforcement Learning for Radio Tracer Localisation in Robotic-assisted Radioguided Surgery

Hanyi Zhang, Kaizhong Deng, Zhaoyang Jacopo Hu, Baoru Huang, Daniel S. Elson

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

Comments Accepted to IEEE International Conference on Robotics and Automation (ICRA) 2025

2501.06946 2025-01-14 cs.RO 80%

Learning Implicit Social Navigation Behavior using Deep Inverse Reinforcement Learning

Tribhi Kathuria, Ke Liu, Junwoo Jang, X. Jessie Yang, Maani Ghaffari

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

Comments 8 pages, Submitted to IEEE Robotics and Automation Letters (RAL)

1. 模仿学习与强化学习 4106 篇

Megaverse: Simulating Embodied Agents at One Million Experiences per Second

Towards a Sample Efficient Reinforcement Learning Pipeline for Vision Based Robotics

Explainable Hierarchical Imitation Learning for Robotic Drink Pouring

Robotic Surgery With Lean Reinforcement Learning

MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale

Bayesian Meta-Learning for Few-Shot Policy Adaptation Across Robotic Platforms

MAMBPO: Sample-efficient multi-robot reinforcement learning using learned world models

Local Navigation and Docking of an Autonomous Robot Mower using Reinforcement Learning and Computer Vision

Reinforcement Learning Approaches in Social Robotics

A review of motion planning algorithms for intelligent robotics

Modeling Social Interaction for Baby in Simulated Environment for Developmental Robotics

myGym: Modular Toolkit for Visuomotor Robotic Tasks

Deep Reinforcement Learning for Navigation in AAA Video Games

Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks

Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning

Efficient Robotic Task Generalization Using Deep Model Fusion Reinforcement Learning

A Comparison of Action Spaces for Learning Manipulation Tasks

Reinforcement Learning for Robotics and Control with Active Uncertainty Reduction

A Differentiable Physics Engine for Deep Learning in Robotics

Using Deep Reinforcement Learning for the Continuous Control of Robotic Arms

Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methods

Simultaneous Control and Human Feedback in the Training of a Robotic Agent with Actor-Critic Reinforcement Learning

Information Theoretically Aided Reinforcement Learning for Embodied Agents

On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models

Reinforcement Learning for Active Perception in Autonomous Navigation

The Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems

Human-Robot Navigation using Event-based Cameras and Reinforcement Learning

Cycloidal Quasi-Direct Drive Actuator Designs with Learning-based Torque Estimation for Legged Robotics

Hybrid Deep Reinforcement Learning for Radio Tracer Localisation in Robotic-assisted Radioguided Surgery

Learning Implicit Social Navigation Behavior using Deep Inverse Reinforcement Learning