机器人 / 具身智能 - arXivDaily 专题

2210.10763 2023-06-16 cs.LG cs.CV cs.RO 67%

On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning

Yifan Xu, Nicklas Hansen, Zirui Wang, Yung-Chieh Chan, Hao Su, Zhuowen Tu

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

Comments Project page with code: https://nicklashansen.github.io/xtra

2305.09943 2023-06-12 cs.LG cs.AI cs.RO 67%

Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum

Jigang Kim, Daesol Cho, H. Jin Kim

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

Comments ICML 2023, first two authors contributed equally

2305.14343 2023-05-31 cs.LG cs.AI cs.CV 67%

Video Prediction Models as Rewards for Reinforcement Learning

Alejandro Escontrela, Ademi Adeniji, Wilson Yan, Ajay Jain, Xue Bin Peng, Ken Goldberg, Youngwoon Lee, Danijar Hafner, Pieter Abbeel

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

Comments 22 pages, 18 figures, 4 tables. under review

2210.07426 2023-05-29 cs.LG cs.AI cs.RO 67%

Skill-Based Reinforcement Learning with Intrinsic Reward Matching

Ademi Adeniji, Amber Xie, Pieter Abbeel

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

Comments 16 pages

2305.12886 2023-05-23 cs.RO cs.AI cs.LG math.OC 67%

End-to-End Stable Imitation Learning via Autonomous Neural Dynamic Policies

Dionis Totsila, Konstantinos Chatzilygeroudis, Denis Hadjivelichkov, Valerio Modugno, Ioannis Hatzilygeroudis, Dimitrios Kanoulas

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

Comments 6 pages, 7 figures, Accepted at the Life-Long Learning with Human Help(L3H2) ICRA 2023 Workshop

2305.12216 2023-05-23 cs.LG cs.AI cs.RO cs.SY eess.SY math.OC 67%

On First-Order Meta-Reinforcement Learning with Moreau Envelopes

Mohammad Taha Toghani, Sebastian Perez-Salazar, César A. Uribe

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

2305.11107 2023-05-19 q-bio.NC cs.AI cs.LG cs.NE cs.RO 67%

From Data-Fitting to Discovery: Interpreting the Neural Dynamics of Motor Control through Reinforcement Learning

Eugene R. Rush, Kaushik Jayaram, J. Sean Humbert

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

2305.09793 2023-05-18 cs.RO cs.AI cs.LG cs.SY eess.SY 67%

Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions

Desong Du, Shaohang Han, Naiming Qi, Haitham Bou Ammar, Jun Wang, Wei Pan

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

2305.04750 2023-05-09 cs.RO cs.AI cs.LG 67%

Sense, Imagine, Act: Multimodal Perception Improves Model-Based Reinforcement Learning for Head-to-Head Autonomous Racing

Elena Shrestha, Chetan Reddy, Hanxi Wan, Yulun Zhuang, Ram Vasudevan

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

2201.08115 2023-04-26 cs.AI cs.LG cs.RO stat.ML 67%

Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning

Sasha Salter, Kristian Hartikainen, Walter Goodwin, Ingmar Posner

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

Journal ref Published at the International Conference on Learning Representations, 2023

2304.09831 2023-04-20 cs.RO cs.AI cs.LG 67%

FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing

Kyle Stachowicz, Dhruv Shah, Arjun Bhorkar, Ilya Kostrikov, Sergey Levine

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

2304.06281 2023-04-14 cs.LG cs.AI cs.MA cs.RO 67%

Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning

Wenli Xiao, Yiwei Lyu, John Dolan

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

Comments Accepted in AAMAS 2023

2303.15178 2023-04-04 cs.LG cs.AI cs.RO 67%

Robust Path Following on Rivers Using Bootstrapped Reinforcement Learning

Niklas Paulig, Ostap Okhrin

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

2303.13489 2023-03-29 cs.LG cs.AI cs.RO 67%

Boosting Reinforcement Learning and Planning with Demonstrations: A Survey

Tongzhou Mu, Hao Su

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

2301.07302 2023-03-28 cs.LG cs.AI cs.RO 67%

PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav

Ram Ramrakhya, Dhruv Batra, Erik Wijmans, Abhishek Das

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

Comments 8 pages + supplement

2303.02234 2023-03-10 cs.RO cs.AI cs.LG cs.NE 67%

Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning

Simon Guist, Jan Schneider, Alexander Dittrich, Vincent Berenz, Bernhard Schölkopf, Dieter Büchler

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

2211.08064 2023-03-08 cs.LG cs.AI cs.CV cs.NA math.NA 67%

Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications

Zhongkai Hao, Songming Liu, Yichi Zhang, Chengyang Ying, Yao Feng, Hang Su, Jun Zhu

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

2303.01859 2023-03-06 cs.LG cs.AI cs.RO 67%

POPGym: Benchmarking Partially Observable Reinforcement Learning

Steven Morad, Ryan Kortvelesy, Matteo Bettini, Stephan Liwicki, Amanda Prorok

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

2210.00498 2023-02-23 cs.LG cs.AI cs.RO 67%

EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model

Yifu Yuan, Jianye Hao, Fei Ni, Yao Mu, Yan Zheng, Yujing Hu, Jinyi Liu, Yingfeng Chen, Changjie Fan

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

Comments Published as a conference paper at ICLR 2023

2302.10446 2023-02-22 cs.RO cs.AI cs.LG 67%

Deep Reinforcement Learning Based on Local GNN for Goal-conditioned Deformable Object Rearranging

Yuhong Deng, Chongkun Xia, Xueqian Wang, Lipeng Chen

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

Comments has been accepted by IEEE/RSJ International Conference on Intelligent Robots and Systems 2022

Journal ref IEEE/RSJ International Conference on Intelligent Robots and Systems 2022 (IROS 2022)

2302.09772 2023-02-21 cs.RO cs.AI cs.LG 67%

Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot

Tao Huang, Kai Chen, Bin Li, Yun-Hui Liu, Qi Dou

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

Comments Accepted to ICRA 2023

2209.07899 2023-02-14 cs.RO cs.AI cs.LG 67%

Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions

Chenhao Li, Sebastian Blaes, Pavel Kolev, Marin Vlastelica, Jonas Frey, Georg Martius

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

2110.08586 2023-02-08 cs.RO cs.AI cs.LG cs.SY eess.SY 67%

Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments

Gustavo Claudio Karl Couto, Eric Aislan Antonelo

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

Journal ref 2021 IEEE Symposium Series on Computational Intelligence (SSCI)

2210.08642 2023-01-18 cs.LG cs.AI cs.RO stat.ML 67%

Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data

Allen Nie, Yannis Flet-Berliac, Deon R. Jordan, William Steenbergen, Emma Brunskill

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

Comments 32 pages. Published at NeurIPS 2022. Presented at RLDM 2022

2205.07150 2023-01-02 eess.SY cs.AI cs.LG cs.RO cs.SY 67%

Interpretable Stochastic Model Predictive Control using Distributional Reinforced Estimation for Quadrotor Tracking Systems

Yanran Wang, James O'Keeffe, Qiuchen Qian, David Boyle

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

Comments 8 pages, 4 figures

2212.01737 2022-12-14 cs.CV cs.AI cs.LG 67%

RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning

Boxuan Zhao, Jun Zhang, Deheng Ye, Jian Cao, Xiao Han, Qiang Fu, Wei Yang

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

Comments accepted by AAAI 2023

2212.05698 2022-12-13 cs.LG cs.AI cs.RO 67%

MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations

Nicklas Hansen, Yixin Lin, Hao Su, Xiaolong Wang, Vikash Kumar, Aravind Rajeswaran

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

2206.11693 2022-11-22 cs.RO cs.AI cs.LG 67%

Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations

Chenhao Li, Marin Vlastelica, Sebastian Blaes, Jonas Frey, Felix Grimminger, Georg Martius

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

2211.02193 2022-11-07 cs.NE cs.AI cs.LG cs.RO 67%

Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning

Manon Flageat, Bryan Lim, Luca Grillotti, Maxime Allard, Simón C. Smith, Antoine Cully

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

Comments Accepted at GECCO Workshop on Quality Diversity Algorithm Benchmarks

2210.11348 2022-10-21 cs.LG cs.AI cs.RO 67%

Hypernetworks in Meta-Reinforcement Learning

Jacob Beck, Matthew Thomas Jackson, Risto Vuorio, Shimon Whiteson

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

Comments Published at CoRL 2022

1. 模仿学习与强化学习 4124 篇

On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning

Demonstration-free Autonomous Reinforcement Learning via Implicit and Bidirectional Curriculum

Video Prediction Models as Rewards for Reinforcement Learning

Skill-Based Reinforcement Learning with Intrinsic Reward Matching

End-to-End Stable Imitation Learning via Autonomous Neural Dynamic Policies

On First-Order Meta-Reinforcement Learning with Moreau Envelopes

From Data-Fitting to Discovery: Interpreting the Neural Dynamics of Motor Control through Reinforcement Learning

Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions

Sense, Imagine, Act: Multimodal Perception Improves Model-Based Reinforcement Learning for Head-to-Head Autonomous Racing

Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning

FastRLAP: A System for Learning High-Speed Driving via Deep RL and Autonomous Practicing

Model-based Dynamic Shielding for Safe and Efficient Multi-Agent Reinforcement Learning

Robust Path Following on Rivers Using Bootstrapped Reinforcement Learning

Boosting Reinforcement Learning and Planning with Demonstrations: A Survey

PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav

Hindsight States: Blending Sim and Real Task Elements for Efficient Reinforcement Learning

Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications

POPGym: Benchmarking Partially Observable Reinforcement Learning

EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model

Deep Reinforcement Learning Based on Local GNN for Goal-conditioned Deformable Object Rearranging

Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot

Versatile Skill Control via Self-supervised Adversarial Imitation of Unlabeled Mixed Motions

Generative Adversarial Imitation Learning for End-to-End Autonomous Driving on Urban Environments

Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data

Interpretable Stochastic Model Predictive Control using Distributional Reinforced Estimation for Quadrotor Tracking Systems

RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning

MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations

Learning Agile Skills via Adversarial Imitation of Rough Partial Demonstrations

Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning

Hypernetworks in Meta-Reinforcement Learning