机器人 / 具身智能 - arXivDaily 专题

2112.13937 2021-12-30 cs.AI cs.RO 62%

Multiagent Model-based Credit Assignment for Continuous Control

Dongge Han, Chris Xiaoxuan Lu, Tomasz Michalak, Michael Wooldridge

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

Comments To Appear in AAMAS2022 (Oral)

2112.11731 2021-12-23 cs.LG cs.AI 62%

Graph augmented Deep Reinforcement Learning in the GameRLand3D environment

Edward Beeching, Maxim Peter, Philippe Marcotte, Jilles Debangoye, Olivier Simonin, Joshua Romoff, Christian Wolf

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

2112.07031 2021-12-15 cs.LG cs.RO 62%

Teaching a Robot to Walk Using Reinforcement Learning

Jack Dibachi, Jacob Azoulay

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

Comments 6 pages, 9 figures

2112.06063 2021-12-14 cs.LG cs.AI cs.CR 62%

MedAttacker: Exploring Black-Box Adversarial Attacks on Risk Prediction Models in Healthcare

Muchao Ye, Junyu Luo, Guanjie Zheng, Cao Xiao, Ting Wang, Fenglong Ma

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

2104.05043 2021-12-14 cs.LG cs.RO 62%

Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning

Jinxin Liu, Donglin Wang, Qiangxing Tian, Zhengyu Chen

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

Comments Accepted by AAAI-22

2112.02278 2021-12-07 cs.RO cs.AI 62%

Stage Conscious Attention Network (SCAN) : A Demonstration-Conditioned Policy for Few-Shot Imitation

Jia-Fong Yeh, Chi-Ming Chung, Hung-Ting Su, Yi-Ting Chen, Winston H. Hsu

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

Comments Accepted by AAAI 2022, preprint version, first two authors contribute equally

2106.02757 2021-11-23 cs.LG cs.AI 62%

Heuristic-Guided Reinforcement Learning

Ching-An Cheng, Andrey Kolobov, Adith Swaminathan

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

2105.03061 2021-11-19 eess.IV cs.AI cs.LG eess.SP 62%

Deep reinforcement learning-designed radiofrequency waveform in MRI

Dongmyung Shin, Younghoon Kim, Chungseok Oh, Hongjun An, Juhyung Park, Jiye Kim, Jongho Lee

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

Comments Published at Nature Machine Intelligence

1912.02368 2021-11-19 cs.LG cs.AI stat.ML 62%

Inter-Level Cooperation in Hierarchical Reinforcement Learning

Abdul Rahman Kreidieh, Glen Berseth, Brandon Trabucco, Samyak Parajuli, Sergey Levine, Alexandre M. Bayen

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

2008.02790 2021-11-15 cs.LG cs.AI stat.ML 62%

Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices

Evan Zheran Liu, Aditi Raghunathan, Percy Liang, Chelsea Finn

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

Comments International Conference on Machine Learning (ICML), 2021

2103.03991 2021-11-03 cs.RO cs.AI 62%

Passing Through Narrow Gaps with Deep Reinforcement Learning

Brendan Tidd, Akansel Cosgun, Jurgen Leitner, Nicolas Hudson

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

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

Journal ref In proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2021

2110.14565 2021-10-28 cs.LG cs.AI 62%

DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations

Fei Deng, Ingook Jang, Sungjin Ahn

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

2106.09422 2021-10-19 cs.RO cs.AI 62%

CRIL: Continual Robot Imitation Learning via Generative and Prediction Model

Chongkai Gao, Haichuan Gao, Shangqi Guo, Tianren Zhang, Feng Chen

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

Journal ref 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

1909.09505 2021-10-14 cs.LG cs.RO eess.SP 62%

Redirection Controller Using Reinforcement Learning

Yuchen Chang, Keigo Matsumoto, Takuji Narumi, Tomohiro Tanikawa, Michitaka Hirose

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

Comments 16 pages, 12 figures, IEEE Access early access

2110.01954 2021-10-06 cs.RO cs.LG 62%

Continuous-Time Fitted Value Iteration for Robust Policies

Michael Lutter, Boris Belousov, Shie Mannor, Dieter Fox, Animesh Garg, Jan Peters

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

Comments arXiv admin note: text overlap with arXiv:2105.12189

2109.15147 2021-10-01 cs.AI cs.LG 62%

Reinforcement Learning with Information-Theoretic Actuation

Elliot Catt, Marcus Hutter, Joel Veness

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

2103.00806 2021-10-01 cs.CV cs.RO 62%

Representation Learning for Event-based Visuomotor Policies

Sai Vemprala, Sami Mian, Ashish Kapoor

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

2103.04780 2021-09-29 cs.LG cs.AI 62%

A Dual-Memory Architecture for Reinforcement Learning on Neuromorphic Platforms

Wilkie Olin-Ammentorp, Yury Sokolov, Maxim Bazhenov

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

Comments 20 pages, 6 figures

2109.08973 2021-09-21 cs.RO cs.AI 62%

Hierarchical Policy for Non-prehensile Multi-object Rearrangement with Deep Reinforcement Learning and Monte Carlo Tree Search

Fan Bai, Fei Meng, Jianbang Liu, Jiankun Wang, Max Q. -H. Meng

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

2109.05940 2021-09-14 cs.RO cs.LG 62%

Cross Domain Robot Imitation with Invariant Representation

Zhao-Heng Yin, Lingfeng Sun, Hengbo Ma, Masayoshi Tomizuka, Wu-Jun Li

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

2012.09156 2021-09-02 cs.LG cs.RO 62%

Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning

Nathan O. Lambert, Albert Wilcox, Howard Zhang, Kristofer S. J. Pister, Roberto Calandra

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

Comments 8 pages, +4 pages appendix

2108.11623 2021-08-27 cs.LG cs.RO cs.SY eess.SY 62%

Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian

Baiyu Peng, Jingliang Duan, Jianyu Chen, Shengbo Eben Li, Genjin Xie, Congsheng Zhang, Yang Guan, Yao Mu, Enxin Sun

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

2108.11510 2021-08-27 cs.CV cs.AI 62%

Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey

Ngan Le, Vidhiwar Singh Rathour, Kashu Yamazaki, Khoa Luu, Marios Savvides

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

2010.04444 2021-08-23 cs.LG cs.AI 62%

Jointly-Learned State-Action Embedding for Efficient Reinforcement Learning

Paul J. Pritz, Liang Ma, Kin K. Leung

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

2108.06526 2021-08-17 cs.LG cs.AI 62%

Fractional Transfer Learning for Deep Model-Based Reinforcement Learning

Remo Sasso, Matthia Sabatelli, Marco A. Wiering

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

Comments 21 pages, 8 figures, 7 tables

2104.11434 2021-08-17 eess.SY cs.LG cs.RO cs.SY 62%

Graph Neural Network Reinforcement Learning for Autonomous Mobility-on-Demand Systems

Daniele Gammelli, Kaidi Yang, James Harrison, Filipe Rodrigues, Francisco C. Pereira, Marco Pavone

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

2103.08624 2021-08-03 cs.RO cs.AI 62%

Autonomous Drone Racing with Deep Reinforcement Learning

Yunlong Song, Mats Steinweg, Elia Kaufmann, Davide Scaramuzza

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

Comments This paper has been accepted for publication at the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, 2021. Copyright @ IEEE

2010.08052 2021-08-03 cs.RO cs.AI 62%

A Learning Approach to Robot-Agnostic Force-Guided High Precision Assembly

Jieliang Luo, Hui Li

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

Comments 7 pages, 6 figures; accepted to IROS 2021

2107.13944 2021-07-30 cs.LG cs.AI stat.ML 62%

Lyapunov-based uncertainty-aware safe reinforcement learning

Ashkan B. Jeddi, Nariman L. Dehghani, Abdollah Shafieezadeh

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

Comments Submitted to IEEE Transactions on Neural Networks and Learning Systems

2107.11811 2021-07-27 cs.LG cs.AI 62%

Reinforced Imitation Learning by Free Energy Principle

Ryoya Ogishima, Izumi Karino, Yasuo Kuniyoshi

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

1. 模仿学习与强化学习 4115 篇

Multiagent Model-based Credit Assignment for Continuous Control

Graph augmented Deep Reinforcement Learning in the GameRLand3D environment

Teaching a Robot to Walk Using Reinforcement Learning

MedAttacker: Exploring Black-Box Adversarial Attacks on Risk Prediction Models in Healthcare

Learn Goal-Conditioned Policy with Intrinsic Motivation for Deep Reinforcement Learning

Stage Conscious Attention Network (SCAN) : A Demonstration-Conditioned Policy for Few-Shot Imitation

Heuristic-Guided Reinforcement Learning

Deep reinforcement learning-designed radiofrequency waveform in MRI

Inter-Level Cooperation in Hierarchical Reinforcement Learning

Decoupling Exploration and Exploitation for Meta-Reinforcement Learning without Sacrifices

Passing Through Narrow Gaps with Deep Reinforcement Learning

DreamerPro: Reconstruction-Free Model-Based Reinforcement Learning with Prototypical Representations

CRIL: Continual Robot Imitation Learning via Generative and Prediction Model

Redirection Controller Using Reinforcement Learning

Continuous-Time Fitted Value Iteration for Robust Policies

Reinforcement Learning with Information-Theoretic Actuation

Representation Learning for Event-based Visuomotor Policies

A Dual-Memory Architecture for Reinforcement Learning on Neuromorphic Platforms

Hierarchical Policy for Non-prehensile Multi-object Rearrangement with Deep Reinforcement Learning and Monte Carlo Tree Search

Cross Domain Robot Imitation with Invariant Representation

Learning Accurate Long-term Dynamics for Model-based Reinforcement Learning

Model-based Chance-Constrained Reinforcement Learning via Separated Proportional-Integral Lagrangian

Deep Reinforcement Learning in Computer Vision: A Comprehensive Survey

Jointly-Learned State-Action Embedding for Efficient Reinforcement Learning

Fractional Transfer Learning for Deep Model-Based Reinforcement Learning

Graph Neural Network Reinforcement Learning for Autonomous Mobility-on-Demand Systems

Autonomous Drone Racing with Deep Reinforcement Learning

A Learning Approach to Robot-Agnostic Force-Guided High Precision Assembly

Lyapunov-based uncertainty-aware safe reinforcement learning

Reinforced Imitation Learning by Free Energy Principle