机器人 / 具身智能 - arXivDaily 专题

2103.04004 2022-02-14 cs.RO cs.SY eess.SY 70%

Bilateral Control-Based Imitation Learning for Velocity-Controlled Robot

Sho Sakaino

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

Comments 6pages, 10 figures, submitted for ISIE2021

Journal ref 2021 IEEE 30th International Symposium on Industrial Electronics (ISIE), pp. 1-6, 2021

2202.03957 2022-02-09 cs.RO cs.AI cs.CV cs.LG 70%

Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning

Stephen James, Pieter Abbeel

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

Comments Project page and code: https://sites.google.com/view/rl-bpp

2112.06424 2021-12-14 cs.LG 70%

A Benchmark for Low-Switching-Cost Reinforcement Learning

Shusheng Xu, Yancheng Liang, Yunfei Li, Simon Shaolei Du, Yi Wu

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

Comments 17 pages, 5 fiugres, project website: https://sites.google.com/view/low-switching-cost-rl

2112.04716 2021-12-10 cs.LG 70%

DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization

Aviral Kumar, Rishabh Agarwal, Tengyu Ma, Aaron Courville, George Tucker, Sergey Levine

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

2106.03443 2021-12-03 cs.LG 70%

Causal Influence Detection for Improving Efficiency in Reinforcement Learning

Maximilian Seitzer, Bernhard Schölkopf, Georg Martius

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

Comments NeurIPS 2021 camera-ready version. Code available at http://github.com/martius-lab/cid-in-rl

2110.15043 2021-10-29 cs.LG 70%

Hindsight Goal Ranking on Replay Buffer for Sparse Reward Environment

Tung M. Luu, Chang D. Yoo

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

Journal ref IEEE Access 2021

2002.09027 2021-10-11 cs.LG eess.SP stat.ML 70%

Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning

Chao-Han Huck Yang, Jun Qi, Pin-Yu Chen, Yi Ouyang, I-Te Danny Hung, Chin-Hui Lee, Xiaoli Ma

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

Comments Accepted to IEEE ICASSP 2020

Journal ref 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

2109.08903 2021-09-27 cs.RO 70%

Density-based Curriculum for Multi-goal Reinforcement Learning with Sparse Rewards

Deyu Yang, Hanbo Zhang, Xuguang Lan, Jishiyu Ding

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

Comments 8 pages, 7 figures

2104.02213 2021-09-14 eess.SY cs.RO cs.SY 70%

Particle MPC for Uncertain and Learning-Based Control

Robert Dyro, James Harrison, Apoorva Sharma, Marco Pavone

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

Comments Accepted to International Conference on Intelligent Robots and Systems (IROS) 2021

2106.08050 2021-06-16 cs.LG 70%

Residual Reinforcement Learning from Demonstrations

Minttu Alakuijala, Gabriel Dulac-Arnold, Julien Mairal, Jean Ponce, Cordelia Schmid

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

2004.08051 2021-04-12 cs.RO cs.AI cs.CV cs.LG 70%

Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning

Keuntaek Lee, Bogdan Vlahov, Jason Gibson, James M. Rehg, Evangelos A. Theodorou

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

2103.09016 2021-03-19 cs.RO 70%

Manipulator-Independent Representations for Visual Imitation

Yuxiang Zhou, Yusuf Aytar, Konstantinos Bousmalis

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

2102.11003 2021-02-24 cs.RO 70%

DROID: Minimizing the Reality Gap using Single-Shot Human Demonstration

Ya-Yen Tsai, Hui Xu, Zihan Ding, Chong Zhang, Edward Johns, Bidan Huang

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

Comments paper accepted and to be published in RA-L 2021

2011.14381 2021-02-09 cs.LG 70%

Self-supervised Visual Reinforcement Learning with Object-centric Representations

Andrii Zadaianchuk, Maximilian Seitzer, Georg Martius

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

2008.06622 2021-01-19 cs.LG stat.ML 70%

Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings

Jesse Zhang, Brian Cheung, Chelsea Finn, Sergey Levine, Dinesh Jayaraman

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

Comments 15 pages, 8 figures, ICML 2020. Website with code: https://sites.google.com/berkeley.edu/carl

Journal ref Proceedings of the 37th International Conference on Machine Learning, PMLR 119:11055-11065, 2020

2010.13957 2021-01-12 cs.LG cs.AI cs.CV cs.RO 70%

MELD: Meta-Reinforcement Learning from Images via Latent State Models

Tony Z. Zhao, Anusha Nagabandi, Kate Rakelly, Chelsea Finn, 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 to CoRL 2020. Supplementary material at https://sites.google.com/view/meld-lsm/home . 16 pages, 19 figures. V2: add funding acknowledgements, reduce file size

2010.09163 2020-12-01 cs.LG 70%

D2RL: Deep Dense Architectures in Reinforcement Learning

Samarth Sinha, Homanga Bharadhwaj, Aravind Srinivas, Animesh Garg

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

Comments NeurIPS 2020 Deep RL Workshop. Preprint. Under review

2003.06417 2020-11-16 cs.LG cs.AI cs.CV cs.RO stat.ML 70%

Sparse Graphical Memory for Robust Planning

Scott Emmons, Ajay Jain, Michael Laskin, Thanard Kurutach, Pieter Abbeel, Deepak Pathak

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

Comments Accepted at NeurIPS 2020. Video and code at https://mishalaskin.github.io/sgm/

2008.02430 2020-11-10 cs.LG stat.ML 70%

Contrastive Variational Reinforcement Learning for Complex Observations

Xiao Ma, Siwei Chen, David Hsu, Wee Sun Lee

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

Comments CoRL 2020 camera ready

2010.15492 2020-11-02 cs.RO 70%

"What, not how": Solving an under-actuated insertion task from scratch

Giulia Vezzani, Michael Neunert, Markus Wulfmeier, Rae Jeong, Thomas Lampe, Noah Siegel, Roland Hafner, Abbas Abdolmaleki, Martin Riedmiller, Francesco Nori

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

2010.13839 2020-10-28 cs.LG cs.CL 70%

VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning

Thomas Carta, Subhajit Chaudhury, Kartik Talamadupula, Michiaki Tatsubori

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

Comments Code is available at http://ibm.biz/VisualHints

2010.09387 2020-10-20 cs.AI 70%

Evaluating the Safety of Deep Reinforcement Learning Models using Semi-Formal Verification

Davide Corsi, Enrico Marchesini, Alessandro Farinelli

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

2009.12877 2020-09-29 cs.CV 70%

Virtual Experience to Real World Application: Sidewalk Obstacle Avoidance Using Reinforcement Learning for Visually Impaired

Faruk Ahmed, Md Sultan Mahmud, Kazi Ashraf Moinuddin, Mohammed Istiaque Hyder, Mohammed Yeasin

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

Comments Journal, to be submitted

2009.05085 2020-09-14 cs.RO 70%

Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learning

Lucas Manuelli, Yunzhu Li, Pete Florence, Russ Tedrake

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

2005.03987 2020-05-11 cs.RO 70%

Coping with the variability in humans reward during simulated human-robot interactions through the coordination of multiple learning strategies

Rémi Dromnelle, Benoît Girard, Erwan Renaudo, Raja Chatila, Mehdi Khamassi

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

Comments 6 pages, 5 figures, written for the RO-MAN 2020 conference. arXiv admin note: text overlap with arXiv:2004.14698

1901.11529 2019-10-31 cs.AI 70%

Addressing Sample Complexity in Visual Tasks Using HER and Hallucinatory GANs

Himanshu Sahni, Toby Buckley, Pieter Abbeel, Ilya Kuzovkin

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

Comments To appear in Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada. Code available at https://github.com/offworld-projects/research-halgan

1905.04100 2019-05-13 cs.NE cs.RO 70%

Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization

Adarsh Sehgal, Hung Manh La, Sushil J. Louis, Hai Nguyen

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

1807.02264 2019-02-28 cs.LG stat.ML 70%

Variance Reduction for Reinforcement Learning in Input-Driven Environments

Hongzi Mao, Shaileshh Bojja Venkatakrishnan, Malte Schwarzkopf, Mohammad Alizadeh

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

1806.05134 2019-02-19 cs.LG stat.ML 70%

Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications

Carson Eisenach, Haichuan Yang, Ji Liu, Han Liu

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

1809.06146 2019-02-14 cs.LG stat.ML 70%

Curriculum goal masking for continuous deep reinforcement learning

Manfred Eppe, Sven Magg, Stefan Wermter

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

1. 模仿学习与强化学习 4124 篇

Bilateral Control-Based Imitation Learning for Velocity-Controlled Robot

Bingham Policy Parameterization for 3D Rotations in Reinforcement Learning

A Benchmark for Low-Switching-Cost Reinforcement Learning

DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization

Causal Influence Detection for Improving Efficiency in Reinforcement Learning

Hindsight Goal Ranking on Replay Buffer for Sparse Reward Environment

Enhanced Adversarial Strategically-Timed Attacks against Deep Reinforcement Learning

Density-based Curriculum for Multi-goal Reinforcement Learning with Sparse Rewards

Particle MPC for Uncertain and Learning-Based Control

Residual Reinforcement Learning from Demonstrations

Approximate Inverse Reinforcement Learning from Vision-based Imitation Learning

Manipulator-Independent Representations for Visual Imitation

DROID: Minimizing the Reality Gap using Single-Shot Human Demonstration

Self-supervised Visual Reinforcement Learning with Object-centric Representations

Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings

MELD: Meta-Reinforcement Learning from Images via Latent State Models

D2RL: Deep Dense Architectures in Reinforcement Learning

Sparse Graphical Memory for Robust Planning

Contrastive Variational Reinforcement Learning for Complex Observations

"What, not how": Solving an under-actuated insertion task from scratch

VisualHints: A Visual-Lingual Environment for Multimodal Reinforcement Learning

Evaluating the Safety of Deep Reinforcement Learning Models using Semi-Formal Verification

Virtual Experience to Real World Application: Sidewalk Obstacle Avoidance Using Reinforcement Learning for Visually Impaired

Keypoints into the Future: Self-Supervised Correspondence in Model-Based Reinforcement Learning

Coping with the variability in humans reward during simulated human-robot interactions through the coordination of multiple learning strategies

Addressing Sample Complexity in Visual Tasks Using HER and Hallucinatory GANs

Deep Reinforcement Learning using Genetic Algorithm for Parameter Optimization

Variance Reduction for Reinforcement Learning in Input-Driven Environments

Marginal Policy Gradients: A Unified Family of Estimators for Bounded Action Spaces with Applications

Curriculum goal masking for continuous deep reinforcement learning