机器人 / 具身智能 - arXivDaily 专题

2209.00347 2023-05-25 cs.LG cs.AI 62%

Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization

Tiantian Zhang, Zichuan Lin, Yuxing Wang, Deheng Ye, Qiang Fu, Wei Yang, Xueqian Wang, Bin Liang, Bo Yuan, Xiu Li

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

Comments Accepted by IEEE Transactions on Neural Networks and Learning Systems, 2023

2305.13741 2023-05-24 cs.LG cs.AI 62%

L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning

Kibeom Kim, Hyundo Lee, Min Whoo Lee, Moonheon Lee, Minsu Lee, Byoung-Tak Zhang

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

Comments 17 pages include appendices, it is under-review

2305.12663 2023-05-23 cs.LG cs.AI 62%

TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching

Yecheng Jason Ma, Kausik Sivakumar, Jason Yan, Osbert Bastani, Dinesh Jayaraman

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

Comments L4DC 2023; Project website: https://penn-pal-lab.github.io/TOM/

2209.11596 2023-05-23 cs.LG cs.RO 62%

Quantification before Selection: Active Dynamics Preference for Robust Reinforcement Learning

Kang Xu, Yan Ma, Wei Li

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

2305.10411 2023-05-18 cs.LG cs.RO 62%

Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies

Hanna Ziesche, Leonel Rozo

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

2107.05818 2023-05-18 cs.LG cs.RO 62%

A Hierarchical Bayesian model for Inverse RL in Partially-Controlled Environments

Kenneth Bogert, Prashant Doshi

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

Comments 8 pages, 10 figures

Journal ref Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems. 2022

2211.02127 2023-05-17 cs.MA cs.AI cs.RO 62%

Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

Siddharth Nayak, Kenneth Choi, Wenqi Ding, Sydney Dolan, Karthik Gopalakrishnan, Hamsa Balakrishnan

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

Comments 9 pages, 7 figures, 8 tables, 5 pages appendix, Code: https://github.com/nsidn98/InforMARL

2305.05354 2023-05-11 cs.RO cs.AI 62%

Safe Deep RL for Intraoperative Planning of Pedicle Screw Placement

Yunke Ao, Hooman Esfandiari, Fabio Carrillo, Yarden As, Mazda Farshad, Benjamin F. Grewe, Andreas Krause, Philipp Fuernstahl

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

Comments 10 pages, 4 figures

2305.02901 2023-05-05 cs.LG cs.AI cs.CR 62%

Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning

Dayuan Chen, Jian Zhang, Yuqian Lv, Jinhuan Wang, Hongjie Ni, Shanqing Yu, Zhen Wang, Qi Xuan

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

2302.14188 2023-05-02 cs.RO cs.AI cs.SY eess.SY 62%

Exposure-Based Multi-Agent Inspection of a Tumbling Target Using Deep Reinforcement Learning

Joshua Aurand, Steven Cutlip, Henry Lei, Kendra Lang, Sean Phillips

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

2304.14533 2023-05-01 cs.LG cs.AI 62%

Adversarial Policy Optimization in Deep Reinforcement Learning

Md Masudur Rahman, Yexiang Xue

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

2204.00117 2023-05-01 cs.RO cs.LG 62%

Visual-Tactile Multimodality for Following Deformable Linear Objects Using Reinforcement Learning

Leszek Pecyna, Siyuan Dong, Shan Luo

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

Comments 8 pages, 11 figures

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

2201.02135 2023-04-25 cs.AI cs.LG 62%

Deep Reinforcement Learning, a textbook

Aske Plaat

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

Comments Revised version 2023, added description of Monte Carlo sampling and N-step algorithm, improved explanation of on-policy and off-policy learning. Preprint available by permission of Publisher

2304.10704 2023-04-24 cs.LG cs.AI 62%

Interactive System-wise Anomaly Detection

Guanchu Wang, Ninghao Liu, Daochen Zha, Xia Hu

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

2304.09869 2023-04-21 cs.NE cs.AI cs.LG 62%

Evolving Constrained Reinforcement Learning Policy

Chengpeng Hu, Jiyuan Pei, Jialin Liu, Xin Yao

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

Comments accepted by the 2023 International Joint Conference on Neural Networks (IJCNN)

2211.04786 2023-04-18 cs.RO cs.AI 62%

Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration

Alexandre Chenu, Olivier Serris, Olivier Sigaud, Nicolas Perrin-Gilbert

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

2304.07425 2023-04-18 cs.LG cs.AI cs.NE 62%

Efficient Quality-Diversity Optimization through Diverse Quality Species

Ryan Wickman, Bibek Poudel, Michael Villarreal, Xiaofei Zhang, Weizi Li

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

2304.05959 2023-04-13 cs.RO cs.AI 62%

UAV Obstacle Avoidance by Human-in-the-Loop Reinforcement in Arbitrary 3D Environment

Xuyang Li, Jianwu Fang, Kai Du, Kuizhi Mei, Jianru Xue

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

Comments accepted in CCC2023

2304.02801 2023-04-07 cs.RO cs.AI 62%

End-to-end Manipulator Calligraphy Planning via Variational Imitation Learning

Fangping Xie, Pierre Le Meur, Charith Fernando

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

Comments 5 pages, 4 figures

2304.00732 2023-04-04 cs.RO cs.LG 62%

Leveraging Predictive Models for Adaptive Sampling of Spatiotemporal Fluid Processes

Sandeep Manjanna, Tom Z. Jiahao, M. Ani Hsieh

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

2201.08355 2023-04-04 cs.RO cs.LG 62%

Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees

Kai-Chieh Hsu, Allen Z. Ren, Duy Phuong Nguyen, Anirudha Majumdar, Jaime F. Fisac

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

Comments Accepted to Special Issue on Risk-aware Autonomous Systems: Theory and Practice, Artificial Intelligence

2007.00691 2023-03-21 cs.RO cs.FL cs.LG 62%

Falsification-Based Robust Adversarial Reinforcement Learning

Xiao Wang, Saasha Nair, Matthias Althoff

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

Comments 8 pages, 4 figures

Journal ref IEEE International Conference on Machine Learning and Applications (ICMLA), 2020, pp. 205-212

2210.07241 2023-03-16 cs.LG cs.RO 62%

Visual Reinforcement Learning with Self-Supervised 3D Representations

Yanjie Ze, Nicklas Hansen, Yinbo Chen, Mohit Jain, Xiaolong Wang

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

Comments Accepted in RA-L 2023 and IROS 2023. Project page: https://yanjieze.com/3d4rl/

2303.04592 2023-03-09 cs.LG cs.AI 62%

Controlled Diversity with Preference : Towards Learning a Diverse Set of Desired Skills

Maxence Hussonnois, Thommen George Karimpanal, Santu Rana

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

Comments Accepted to AAMAS 2023

Journal ref AAMAS 2023

2206.07376 2023-03-09 cs.LG cs.AI 62%

Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning

Xiaoteng Ma, Shuai Ma, Li Xia, Qianchuan Zhao

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

Comments Accecpted by Journal of Artificial Intelligence Research

Journal ref Journal of Artificial Intelligence Research 75 (2022) 569-595

2303.04129 2023-03-08 cs.AI cs.LG 62%

Foundation Models for Decision Making: Problems, Methods, and Opportunities

Sherry Yang, Ofir Nachum, Yilun Du, Jason Wei, Pieter Abbeel, Dale Schuurmans

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

2303.04118 2023-03-08 cs.RO cs.LG 62%

A Multiplicative Value Function for Safe and Efficient Reinforcement Learning

Nick Bührer, Zhejun Zhang, Alexander Liniger, Fisher Yu, Luc Van Gool

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

Comments Repository available at https://github.com/nikeke19/Safe-Mult-RL

2109.02823 2023-03-07 cs.RO cs.AI 62%

Learning Visual-Audio Representations for Voice-Controlled Robots

Peixin Chang, Shuijing Liu, D. Livingston McPherson, Katherine Driggs-Campbell

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

Comments Published in ICRA 2023

2210.01525 2023-03-06 cs.RO cs.LG 62%

Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control

Murad Dawood, Nils Dengler, Jorge de Heuvel, Maren Bennewitz

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

Comments Accepted for ICRA2023

2210.15206 2023-02-28 cs.RO cs.LG 62%

Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision

Ashvin Nair, Brian Zhu, Gokul Narayanan, Eugen Solowjow, Sergey Levine

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

Comments 10 pages. To be presented at ICRA 2023

1. 模仿学习与强化学习 4134 篇

Dynamics-Adaptive Continual Reinforcement Learning via Progressive Contextualization

L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning

TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching

Quantification before Selection: Active Dynamics Preference for Robust Reinforcement Learning

Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies

A Hierarchical Bayesian model for Inverse RL in Partially-Controlled Environments

Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation

Safe Deep RL for Intraoperative Planning of Pedicle Screw Placement

Single Node Injection Label Specificity Attack on Graph Neural Networks via Reinforcement Learning

Exposure-Based Multi-Agent Inspection of a Tumbling Target Using Deep Reinforcement Learning

Adversarial Policy Optimization in Deep Reinforcement Learning

Visual-Tactile Multimodality for Following Deformable Linear Objects Using Reinforcement Learning

Deep Reinforcement Learning, a textbook

Interactive System-wise Anomaly Detection

Evolving Constrained Reinforcement Learning Policy

Leveraging Sequentiality in Reinforcement Learning from a Single Demonstration

Efficient Quality-Diversity Optimization through Diverse Quality Species

UAV Obstacle Avoidance by Human-in-the-Loop Reinforcement in Arbitrary 3D Environment

End-to-end Manipulator Calligraphy Planning via Variational Imitation Learning

Leveraging Predictive Models for Adaptive Sampling of Spatiotemporal Fluid Processes

Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees

Falsification-Based Robust Adversarial Reinforcement Learning

Visual Reinforcement Learning with Self-Supervised 3D Representations

Controlled Diversity with Preference : Towards Learning a Diverse Set of Desired Skills

Mean-Semivariance Policy Optimization via Risk-Averse Reinforcement Learning

Foundation Models for Decision Making: Problems, Methods, and Opportunities

A Multiplicative Value Function for Safe and Efficient Reinforcement Learning

Learning Visual-Audio Representations for Voice-Controlled Robots

Handling Sparse Rewards in Reinforcement Learning Using Model Predictive Control

Learning on the Job: Self-Rewarding Offline-to-Online Finetuning for Industrial Insertion of Novel Connectors from Vision