机器人 / 具身智能 - arXivDaily 专题

2107.03685 2022-11-28 cs.RO cs.AI 73%

Towards Autonomous Pipeline Inspection with Hierarchical Reinforcement Learning

Nicolò Botteghi, Luuk Grefte, Mannes Poel, Beril Sirmacek, Christoph Brune, Edwin Dertien, Stefano Stramigioli

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

2211.12930 2022-11-24 cs.RO cs.AI 73%

Introspection-based Explainable Reinforcement Learning in Episodic and Non-episodic Scenarios

Niclas Schroeter, Francisco Cruz, Stefan Wermter

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

2211.11027 2022-11-22 cs.RO cs.LG cs.SY eess.SY 73%

Safe Reinforcement Learning using Data-Driven Predictive Control

Mahmoud Selim, Amr Alanwar, M. Watheq El-Kharashi, Hazem M. Abbas, Karl H. Johansson

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

2206.03023 2022-11-11 cs.LG cs.AI 73%

How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression

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

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

Comments NeurIPS 2022. Project website: https://jasonma2016.github.io/GoFAR/

2210.12272 2022-10-25 stat.ML cs.LG cs.RO 73%

Implicit Offline Reinforcement Learning via Supervised Learning

Alexandre Piche, Rafael Pardinas, David Vazquez, Igor Mordatch, Chris Pal

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

2106.12177 2022-10-24 cs.LG cs.RO 73%

Imitation Learning: Progress, Taxonomies and Challenges

Boyuan Zheng, Sunny Verma, Jianlong Zhou, Ivor Tsang, Fang Chen

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

2210.08412 2022-10-18 cs.LG cs.RO 73%

Towards an Interpretable Hierarchical Agent Framework using Semantic Goals

Bharat Prakash, Nicholas Waytowich, Tim Oates, Tinoosh Mohsenin

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

2210.07553 2022-10-17 cs.RO cs.LG cs.SY eess.SY 73%

Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate

Dongjie Yu, Wenjun Zou, Yujie Yang, Haitong Ma, Shengbo Eben Li, Jingliang Duan, Jianyu Chen

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

Comments 12 pages, 6 figures

2210.02343 2022-10-06 cs.RO cs.LG 73%

Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning

David Brandfonbrener, Stephen Tu, Avi Singh, Stefan Welker, Chad Boodoo, Nikolai Matni, Jake Varley

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

2110.02792 2022-10-04 cs.LG cs.AI 73%

Hierarchical Potential-based Reward Shaping from Task Specifications

Luigi Berducci, Edgar A. Aguilar, Dejan Ničković, Radu Grosu

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

Comments 7 pages main, 5 pages appendix - added f1tenth racing car environment

2208.02680 2022-08-05 cs.RO cs.LG cs.SD eess.AS 73%

Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations

Xufeng Zhao, Cornelius Weber, Muhammad Burhan Hafez, Stefan Wermter

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

Comments Accepted at IROS 2022

2203.13880 2022-06-20 cs.CV cs.AI 73%

Reinforcement Learning with Action-Free Pre-Training from Videos

Younggyo Seo, Kimin Lee, Stephen James, Pieter Abbeel

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

Comments International Conference on Machine Learning (ICML 2022). Project page: https://sites.google.com/view/rl-apv

2206.02855 2022-06-08 cs.LG cs.AI 73%

Efficient entity-based reinforcement learning

Vince Jankovics, Michael Garcia Ortiz, Eduardo Alonso

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

2203.10518 2022-03-22 cs.RO cs.HC cs.LG 73%

Learning on the Job: Long-Term Behavioural Adaptation in Human-Robot Interactions

Francesco Del Duchetto, Marc Hanheide

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

Comments 8 pages, 9 figures

2203.10050 2022-03-21 cs.LG cs.AI 73%

SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning

Jongjin Park, Younggyo Seo, Jinwoo Shin, Honglak Lee, Pieter Abbeel, Kimin Lee

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

Comments Accepted to ICLR 2022

2203.00369 2022-03-02 cs.RO cs.LG 73%

Approximating a deep reinforcement learning docking agent using linear model trees

Vilde B. Gjærum, Ella-Lovise H. Rørvik, Anastasios M. Lekkas

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

2106.09159 2022-02-08 cs.LG cs.RO 73%

Automatic Curricula via Expert Demonstrations

Siyu Dai, Andreas Hofmann, Brian Williams

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

Comments NeurIPS 2021 Deep Reinforcement Learning Workshop

2106.14080 2022-01-31 cs.LG cs.AI stat.ML 73%

Model-Advantage and Value-Aware Models for Model-Based Reinforcement Learning: Bridging the Gap in Theory and Practice

Nirbhay Modhe, Harish Kamath, Dhruv Batra, Ashwin Kalyan

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

2111.12867 2021-11-29 cs.RO cs.LG 73%

Back to Reality for Imitation Learning

Edward Johns

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

Comments Published at CoRL 2021, blue sky oral track

2107.00591 2021-11-02 cs.RO cs.LG 73%

Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble

Seunghyun Lee, Younggyo Seo, Kimin Lee, Pieter Abbeel, Jinwoo Shin

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

Comments CoRL 2021. First two authors contributed equally

2110.14941 2021-10-29 cs.RO cs.LG cs.SY eess.SY 73%

A Novel Sample-efficient Deep Reinforcement Learning with Episodic Policy Transfer for PID-Based Control in Cardiac Catheterization Robots

Olatunji Mumini Omisore, Toluwanimi Akinyemi, Wenke Duan, Wenjing Du, Lei Wang

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

Comments 6 pages, 7 figures

2110.12080 2021-10-26 cs.LG cs.AI 73%

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks

Tianjun Zhang, Benjamin Eysenbach, Ruslan Salakhutdinov, Sergey Levine, Joseph E. Gonzalez

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

1811.10264 2021-10-12 cs.LG cs.AI 73%

PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration Environments

Qihao Liu, Yujia Wang, Xiaofeng Liu

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

Comments Accepted to IROS 2021

2109.14974 2021-10-01 cs.RO cs.LG 73%

Unified Data Collection for Visual-Inertial Calibration via Deep Reinforcement Learning

Yunke Ao, Le Chen, Florian Tschopp, Michel Breyer, Andrei Cramariuc, Roland Siegwart

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

2109.08273 2021-09-20 cs.RO cs.AI 73%

ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning

Ryan Hoque, Ashwin Balakrishna, Ellen Novoseller, Albert Wilcox, Daniel S. Brown, Ken Goldberg

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

Comments CoRL 2021 Oral

1810.07483 2021-08-05 cs.RO cs.LG 73%

O2A: One-shot Observational learning with Action vectors

Leo Pauly, Wisdom C. Agboh, David C. Hogg, Raul Fuentes

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

Journal ref Front. Robot. AI 8:686368 (2021)

2007.16044 2021-08-02 cs.LG cs.AI 73%

Low Dimensional State Representation Learning with Reward-shaped Priors

Nicolò Botteghi, Ruben Obbink, Daan Geijs, Mannes Poel, Beril Sirmacek, Christoph Brune, Abeje Mersha, Stefano Stramigioli

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

Comments Paper Accepted at ICPR2020

Journal ref Conference Proceedings 25th International Conference on Pattern Recognition (ICPR), 1, 2021, 3736-3743

2106.05091 2021-06-10 cs.LG cs.AI 73%

PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training

Kimin Lee, Laura Smith, Pieter Abbeel

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

Comments ICML 2021. First two authors contributed equally. Website: https://sites.google.com/view/icml21pebble Code: https://github.com/pokaxpoka/B_Pref

2012.01934 2021-05-27 cs.LG cs.AI cs.HC cs.MA 73%

Adaptable Automation with Modular Deep Reinforcement Learning and Policy Transfer

Zohreh Raziei, Mohsen Moghaddam

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

Comments 32 pages, 13 Figures, Presented at 2020 INFORMS Annual Meeting

2010.06962 2021-05-26 cs.LG cs.AI 73%

Self-Imitation Learning for Robot Tasks with Sparse and Delayed Rewards

Zhixin Chen, Mengxiang Lin

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

Comments 6 pages, 5 figures

1. 模仿学习与强化学习 4111 篇

Towards Autonomous Pipeline Inspection with Hierarchical Reinforcement Learning

Introspection-based Explainable Reinforcement Learning in Episodic and Non-episodic Scenarios

Safe Reinforcement Learning using Data-Driven Predictive Control

How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression

Implicit Offline Reinforcement Learning via Supervised Learning

Imitation Learning: Progress, Taxonomies and Challenges

Towards an Interpretable Hierarchical Agent Framework using Semantic Goals

Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate

Visual Backtracking Teleoperation: A Data Collection Protocol for Offline Image-Based Reinforcement Learning

Hierarchical Potential-based Reward Shaping from Task Specifications

Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations

Reinforcement Learning with Action-Free Pre-Training from Videos

Efficient entity-based reinforcement learning

Learning on the Job: Long-Term Behavioural Adaptation in Human-Robot Interactions

SURF: Semi-supervised Reward Learning with Data Augmentation for Feedback-efficient Preference-based Reinforcement Learning

Approximating a deep reinforcement learning docking agent using linear model trees

Automatic Curricula via Expert Demonstrations

Model-Advantage and Value-Aware Models for Model-Based Reinforcement Learning: Bridging the Gap in Theory and Practice

Back to Reality for Imitation Learning

Offline-to-Online Reinforcement Learning via Balanced Replay and Pessimistic Q-Ensemble

A Novel Sample-efficient Deep Reinforcement Learning with Episodic Policy Transfer for PID-Based Control in Cardiac Catheterization Robots

C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks

PNS: Population-Guided Novelty Search for Reinforcement Learning in Hard Exploration Environments

Unified Data Collection for Visual-Inertial Calibration via Deep Reinforcement Learning

ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning

O2A: One-shot Observational learning with Action vectors

Low Dimensional State Representation Learning with Reward-shaped Priors

PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training

Adaptable Automation with Modular Deep Reinforcement Learning and Policy Transfer

Self-Imitation Learning for Robot Tasks with Sparse and Delayed Rewards