机器人 / 具身智能 - arXivDaily 专题

1812.05027 2018-12-13 cs.RO 70%

Learning with Training Wheels: Speeding up Training with a Simple Controller for Deep Reinforcement Learning

Linhai Xie, Sen Wang, Stefano Rosa, Andrew Markham, Niki Trigoni

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

Comments Published in ICRA2018. The code is now available at https://github.com/xie9187/AsDDPG

1810.10369 2018-10-25 cs.LG cs.CR stat.ML 70%

The Faults in Our Pi Stars: Security Issues and Open Challenges in Deep Reinforcement Learning

Vahid Behzadan, Arslan Munir

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

Comments arXiv admin note: text overlap with arXiv:1807.06064, arXiv:1712.03632, arXiv:1803.02811, arXiv:1710.00814 by other authors

1810.05017 2018-10-12 cs.LG cs.AI cs.CV cs.RO 70%

One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL

Tom Le Paine, Sergio Gómez Colmenarejo, Ziyu Wang, Scott Reed, Yusuf Aytar, Tobias Pfaff, Matt W. Hoffman, Gabriel Barth-Maron, Serkan Cabi, David Budden, Nando de Freitas

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

1809.06305 2018-09-27 cs.AI 70%

Automata Guided Reinforcement Learning With Demonstrations

Xiao Li, Yao Ma, Calin Belta

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

1806.10322 2018-06-28 cs.AI 70%

The Virtuous Machine - Old Ethics for New Technology?

Nicolas Berberich, Klaus Diepold

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

1707.03374 2018-06-20 cs.LG cs.AI cs.CV cs.NE cs.RO 70%

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation

YuXuan Liu, Abhishek Gupta, Pieter Abbeel, Sergey Levine

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

Comments Accepted at ICRA 2018, Brisbane. YuXuan Liu and Abhishek Gupta had equal contribution

1804.04154 2018-04-13 cs.RO 70%

Reinforcement Learning for UAV Attitude Control

William Koch, Renato Mancuso, Richard West, Azer Bestavros

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

Comments 13 pages, 9 figures

1606.05312 2018-04-13 cs.AI 70%

Successor Features for Transfer in Reinforcement Learning

André Barreto, Will Dabney, Rémi Munos, Jonathan J. Hunt, Tom Schaul, Hado van Hasselt, David Silver

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

Comments Published at NIPS 2017

1802.02395 2018-02-08 cs.RO 70%

Evaluation of Deep Reinforcement Learning Methods for Modular Robots

Risto Kojcev, Nora Etxezarreta, Alejandro Hernández, Víctor Mayoral

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

1703.03078 2017-06-20 cs.RO 70%

Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning

Yevgen Chebotar, Karol Hausman, Marvin Zhang, Gaurav Sukhatme, Stefan Schaal, Sergey Levine

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

Comments Paper accepted to the International Conference on Machine Learning (ICML) 2017

1107.0048 2011-07-04 cs.AI 70%

Reinforcement Learning for Agents with Many Sensors and Actuators Acting in Categorizable Environments

E. Celaya, J. M. Porta

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

Journal ref Journal Of Artificial Intelligence Research, Volume 23, pages 79-122, 2005

2602.03087 2026-07-22 cs.RO cs.AI cs.LG 版本更新 69%

Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing and Descending for Indoor Firefighting: An End-to-End Reinforcement Learning Approach

四足机器人在室内灭火中的自适应爬楼梯训练与仿真：一种端到端强化学习方法

Baixiao Huang, Baiyu Huang, Yu Hou

机构 * Independent Researcher（独立研究者）； Department of Construction Management, Western New England University（西雅图新英格兰大学建设管理系）

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

AI总结本研究提出一种两阶段端到端强化学习方法，用于四足机器人在复杂室内环境中适应不同楼梯形状的爬行任务。

Comments 8 pages, 9 figures, 43rd International Symposium on Automation and Robotics in Construction

2607.06388 2026-07-08 cs.RO cs.CV cs.LG 新提交 69%

Learning to Throw Objects Safely in Multi-Obstacle Environments

学习在多障碍物环境中安全投掷物体

Mohammadreza Kasaei, Klemen Voncina, Hamidreza Kasaei

机构 * University of Groningen（格罗宁根大学）； University of Edinburgh（爱丁堡大学）

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

AI总结研究在多障碍物环境中安全投掷物体的问题，引入势场状态表示，结合动觉演示初始化，用SAC等算法优化，经模拟和真实机器人实验，该表示在成功率和扩展性上表现出色，实现了模拟到真实的可靠迁移。

Comments This paper has been presented at the IEEE International Conference on Robotics & Automation (ICRA), 2026

2605.12771 2026-05-14 cs.RO cs.AI cs.LG cs.SY eess.SY math.OC 69%

Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization

自适应平滑切比雪夫注意力用于多目标策略优化

Alejandro Murillo-Gonzalez, Mahmoud Ali, Lantao Liu

机构 * Indiana University–Bloomington（印第安纳大学布卢明顿分校）

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

AI总结本文提出自适应平滑切比雪夫框架，通过动态调节优化景观曲率，解决多目标强化学习中非凸区域解恢复问题，验证于机器人隐身视觉搜索任务，发现非凸区域的帕累托最优策略。

Comments To appear in the Proceedings of Robotics: Science and Systems (RSS) 2026

2602.11142 2026-02-12 cs.RO cs.AI cs.LG 69%

Data-Efficient Hierarchical Goal-Conditioned Reinforcement Learning via Normalizing Flows

通过归一化流实现数据高效的分层目标条件强化学习

Shaswat Garg, Matin Moezzi, Brandon Da Silva

机构 * ArenaX Labs（ArenaX实验室）

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

AI总结本文提出基于归一化流的分层隐式Q学习框架，通过提升策略表达能力与数据效率，实现更稳健的长周期任务学习。

Comments 9 pages, 3 figures, IEEE International Conference on Robotics and Automation 2026

2503.21406 2025-11-04 cs.AI cs.LG cs.RO 69%

Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning

Leon Keller, Daniel Tanneberg, Jan Peters

机构 * Intelligent Autonomous Systems, TU Darmstadt, Germany（图腾达姆施塔特大学智能自主系统研究所）； German Research Center for AI, Germany（德国人工智能研究中心）； Hessian Centre for Artificial Intelligence, Germany（黑森州人工智能中心）； Honda Research Institute EU, Germany（本田欧洲研究院）

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

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

2409.05344 2024-12-25 cs.RO cs.AI cs.LG 69%

GOPT: Generalizable Online 3D Bin Packing via Transformer-based Deep Reinforcement Learning

Heng Xiong, Changrong Guo, Jian Peng, Kai Ding, Wenjie Chen, Xuchong Qiu, Long Bai, Jianfeng Xu

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

Comments 8 pages, 6 figures. This paper has been accepted by IEEE Robotics and Automation Letters

2410.19693 2024-10-28 cs.RO cs.AI cs.LG 69%

MILES: Making Imitation Learning Easy with Self-Supervision

Georgios Papagiannis, Edward Johns

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

Comments Published at the Conference on Robot Learning (CoRL) 2024

2402.15197 2024-08-14 eess.SY cs.AI cs.LG cs.RO cs.SY 69%

Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization

Homayoun Honari, Mehran Ghafarian Tamizi, Homayoun Najjaran

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

Comments Accepted to the IEEE International Conference on Robotics and Automation (ICRA) 2024, 7 Pages, 3 Figures

2308.07948 2023-12-27 cs.RO cs.AI cs.CV 69%

Leveraging Symmetries in Pick and Place

Haojie Huang, Dian Wang, Arsh Tangri, Robin Walters, Robert Platt

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

Comments International Journal of Robotics Research. arXiv admin note: substantial text overlap with arXiv:2202.09400

2309.01267 2023-11-03 cs.RO cs.AI cs.LG cs.SY eess.SY 69%

Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy

Haimin Hu, Zixu Zhang, Kensuke Nakamura, Andrea Bajcsy, Jaime F. Fisac

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

Comments Conference on Robot Learning 2023

2309.05131 2023-09-12 cs.LG cs.AI cs.RO 69%

Signal Temporal Logic Neural Predictive Control

Yue Meng, Chuchu Fan

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

Comments Accepted by IEEE Robotics and Automation Letters (RA-L) and ICRA2024

2308.13088 2023-08-28 cs.RO cs.AI cs.LG 69%

Racing Towards Reinforcement Learning based control of an Autonomous Formula SAE Car

Aakaash Salvaji, Harry Taylor, David Valencia, Trevor Gee, Henry Williams

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

Comments Accepted at the Australasian Conference on Robotics and Automation (ACRA 2022)

2307.10142 2023-07-20 cs.RO cs.AI cs.LG 69%

Benchmarking Potential Based Rewards for Learning Humanoid Locomotion

Se Hwan Jeon, Steve Heim, Charles Khazoom, Sangbae Kim

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

Journal ref 2023 IEEE International Conference on Robotics and Automation (ICRA), London, United Kingdom, 2023, pp. 9204-9210

2306.09537 2023-06-19 cs.RO cs.AI cs.LG cs.MA cs.SY eess.SY 69%

QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control

Zhehui Huang, Sumeet Batra, Tao Chen, Rahul Krupani, Tushar Kumar, Artem Molchanov, Aleksei Petrenko, James A. Preiss, Zhaojing Yang, Gaurav S. Sukhatme

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

Comments Paper published in ICRA 2023 Workshop: The Role of Robotics Simulators for Unmanned Aerial Vehicles. The workshop can be found in https://imrclab.github.io/workshop-uav-sims-icra2023/

2302.12232 2023-02-24 cs.LG cs.AI cs.RO 69%

Concept Learning for Interpretable Multi-Agent Reinforcement Learning

Renos Zabounidis, Joseph Campbell, Simon Stepputtis, Dana Hughes, Katia Sycara

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

Comments Accepted to the 6th Conference on Robot Learning (CoRL 2022), Auckland, New Zealand

2301.02099 2023-01-06 cs.RO cs.AI cs.LG 69%

Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping

Lina Mezghani, Sainbayar Sukhbaatar, Piotr Bojanowski, Alessandro Lazaric, Karteek Alahari

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

Comments Code: https://github.com/facebookresearch/go-fresh

Journal ref 6th Conference on Robot Learning (CoRL 2022)

2206.01488 2022-12-12 cs.RO cs.AI cs.LG 69%

GIN: Graph-based Interaction-aware Constraint Policy Optimization for Autonomous Driving

Se-Wook Yoo, Chan Kim, Jin-Woo Choi, Seong-Woo Kim, Seung-Woo Seo

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

Comments 8 pages, 7 figures, 4 tables, submission to RA-L in 2022

Journal ref IEEE Robotics and Automation Letters 2022

2205.09251 2022-05-20 cs.LG cs.AI cs.RO 69%

IL-flOw: Imitation Learning from Observation using Normalizing Flows

Wei-Di Chang, Juan Camilo Gamboa Higuera, Scott Fujimoto, David Meger, Gregory Dudek

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

Comments Presented at the 4th Robot Learning Workshop at NeurIPS 2021

2205.05787 2022-05-13 cs.RO cs.AI cs.LG cs.SY eess.SY 69%

Bridging Model-based Safety and Model-free Reinforcement Learning through System Identification of Low Dimensional Linear Models

Zhongyu Li, Jun Zeng, Akshay Thirugnanam, Koushil Sreenath

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

Comments Accepted in Proceedings of Robotics: Science and Systems 2022 (RSS 2022)

1. 模仿学习与强化学习 4113 篇

Learning with Training Wheels: Speeding up Training with a Simple Controller for Deep Reinforcement Learning

The Faults in Our Pi Stars: Security Issues and Open Challenges in Deep Reinforcement Learning

One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL

Automata Guided Reinforcement Learning With Demonstrations

The Virtuous Machine - Old Ethics for New Technology?

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation

Reinforcement Learning for UAV Attitude Control

Successor Features for Transfer in Reinforcement Learning

Evaluation of Deep Reinforcement Learning Methods for Modular Robots

Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning

Reinforcement Learning for Agents with Many Sensors and Actuators Acting in Categorizable Environments

Training and Simulation of Quadrupedal Robot in Adaptive Stair Climbing and Descending for Indoor Firefighting: An End-to-End Reinforcement Learning Approach

Learning to Throw Objects Safely in Multi-Obstacle Environments

Adaptive Smooth Tchebycheff Attention for Multi-Objective Policy Optimization

Data-Efficient Hierarchical Goal-Conditioned Reinforcement Learning via Normalizing Flows

Neuro-Symbolic Imitation Learning: Discovering Symbolic Abstractions for Skill Learning

GOPT: Generalizable Online 3D Bin Packing via Transformer-based Deep Reinforcement Learning

MILES: Making Imitation Learning Easy with Self-Supervision

Safety Optimized Reinforcement Learning via Multi-Objective Policy Optimization

Leveraging Symmetries in Pick and Place

Deception Game: Closing the Safety-Learning Loop in Interactive Robot Autonomy

Signal Temporal Logic Neural Predictive Control

Racing Towards Reinforcement Learning based control of an Autonomous Formula SAE Car

Benchmarking Potential Based Rewards for Learning Humanoid Locomotion

QuadSwarm: A Modular Multi-Quadrotor Simulator for Deep Reinforcement Learning with Direct Thrust Control

Concept Learning for Interpretable Multi-Agent Reinforcement Learning

Learning Goal-Conditioned Policies Offline with Self-Supervised Reward Shaping

GIN: Graph-based Interaction-aware Constraint Policy Optimization for Autonomous Driving

IL-flOw: Imitation Learning from Observation using Normalizing Flows

Bridging Model-based Safety and Model-free Reinforcement Learning through System Identification of Low Dimensional Linear Models