机器人 / 具身智能 - arXivDaily 专题

2106.12142 2022-11-04 cs.LG cs.AI 62%

IQ-Learn: Inverse soft-Q Learning for Imitation

Divyansh Garg, Shuvam Chakraborty, Chris Cundy, Jiaming Song, Matthieu Geist, Stefano Ermon

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

Comments Spotlight in NeurIPS 2021. Winner of '21 MineRL BASALT Challenge. Website: https://div99.github.io/IQ-Learn

2210.17368 2022-11-01 cs.LG cs.AI 62%

Teacher-student curriculum learning for reinforcement learning

Yanick Schraner

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

2210.17296 2022-11-01 cs.LG cs.AI 62%

Using Contrastive Samples for Identifying and Leveraging Possible Causal Relationships in Reinforcement Learning

Harshad Khadilkar, Hardik Meisheri

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

2210.14492 2022-10-27 cs.LG cs.AI stat.ML 62%

Provable Safe Reinforcement Learning with Binary Feedback

Andrew Bennett, Dipendra Misra, Nathan Kallus

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

2210.10195 2022-10-20 cs.LG cs.AI 62%

Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

Peide Huang, Mengdi Xu, Jiacheng Zhu, Laixi Shi, Fei Fang, Ding Zhao

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

Journal ref 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

1907.05707 2022-10-14 cs.LG cs.AI cs.MA 62%

Shapley Q-value: A Local Reward Approach to Solve Global Reward Games

Jianhong Wang, Yuan Zhang, Tae-Kyun Kim, Yunjie Gu

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

Journal ref AAAI 2020

2210.06377 2022-10-13 cs.RO cs.LG 62%

Smooth Trajectory Collision Avoidance through Deep Reinforcement Learning

Sirui Song, Kirk Saunders, Ye Yue, Jundong Liu

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

Comments Accepted to ICMLA 2022

2202.02363 2022-10-13 cs.LG cs.AI cs.NE math.OC 62%

Meta-Reinforcement Learning with Self-Modifying Networks

Mathieu Chalvidal, Thomas Serre, Rufin VanRullen

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

Comments Published at Neurips 2022

2210.00350 2022-10-04 cs.RO cs.LG 62%

Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning

Zheng Wu, Yichen Xie, Wenzhao Lian, Changhao Wang, Yanjiang Guo, Jianyu Chen, Stefan Schaal, Masayoshi Tomizuka

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

Comments 7 pages, 9 figures

2209.15078 2022-10-03 cs.LG cs.RO 62%

Online Weighted Q-Ensembles for Reduced Hyperparameter Tuning in Reinforcement Learning

Renata Garcia, Wouter Caarls

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

2209.14940 2022-09-30 cs.LG cs.AI 62%

Reinforcement Learning Algorithms: An Overview and Classification

Fadi AlMahamid, Katarina Grolinger

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

Journal ref 2021 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE), 2021, pp. 1-7

2209.13489 2022-09-28 cs.LG cs.AI 62%

Reward Learning using Structural Motifs in Inverse Reinforcement Learning

Raeid Saqur

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

2209.12483 2022-09-27 cs.LG cs.AI 62%

Delayed Geometric Discounts: An Alternative Criterion for Reinforcement Learning

Firas Jarboui, Ahmed Akakzia

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

Comments 10 Pages, 9 Figures

2202.09514 2022-09-27 cs.LG cs.AI cs.GT 62%

Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training

Peide Huang, Mengdi Xu, Fei Fang, Ding Zhao

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

2106.08746 2022-09-26 cs.LG cs.AI cs.CR 62%

Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses

Buse G. A. Tekgul, Shelly Wang, Samuel Marchal, N. Asokan

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

Comments Will appear in the proceedings of ESORICS 2022; 13 pages, 6 figures, 6 tables

2209.09536 2022-09-21 cs.LG cs.AI 62%

Towards Task-Prioritized Policy Composition

Finn Rietz, Erik Schaffernicht, Todor Stoyanov, Johannes A. Stork

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

2209.07996 2022-09-19 cs.RO cs.AI 62%

SoLo T-DIRL: Socially-Aware Dynamic Local Planner based on Trajectory-Ranked Deep Inverse Reinforcement Learning

Yifan Xu, Theodor Chakhachiro, Tribhi Kathuria, Maani Ghaffari

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

2209.03800 2022-09-13 cs.RO cs.AI 62%

Double Q-Learning for Citizen Relocation During Natural Hazards

Alysson Ribeiro da Silva

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

Comments Technical Report on Double Q-Learning for Citizen Relocation During Natural Hazards

2209.03859 2022-09-09 cs.MA cs.AI cs.LG 62%

A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning

Kai Cui, Anam Tahir, Gizem Ekinci, Ahmed Elshamanhory, Yannick Eich, Mengguang Li, Heinz Koeppl

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

2207.09372 2022-09-09 cs.RO cs.AI 62%

On Decentralizing Federated Reinforcement Learning in Multi-Robot Scenarios

Jayprakash S. Nair, Divya D. Kulkarni, Ajitem Joshi, Sruthy Suresh

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

Comments Submitted to SEEDA 2022. This arxiv is a preprint and NOT the final version

2209.02954 2022-09-08 cs.RO cs.AI 62%

A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Platform

Z. Jiang, G. Song

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

2208.04822 2022-08-31 cs.LG cs.AI 62%

Generalized Reinforcement Learning: Experience Particles, Action Operator, Reinforcement Field, Memory Association, and Decision Concepts

Po-Hsiang Chiu, Manfred Huber

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

Comments 37 pages, 15 figures

2109.02791 2022-08-29 cs.RO cs.FL cs.LG 62%

Safety-Critical Learning of Robot Control with Temporal Logic Specifications

Mingyu Cai, Cristian-Ioan Vasile

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

Comments Under Review. arXiv admin note: text overlap with arXiv:2102.12855

2105.14363 2022-08-23 cs.LG cs.AI stat.ML 62%

On the Theory of Reinforcement Learning with Once-per-Episode Feedback

Niladri S. Chatterji, Aldo Pacchiano, Peter L. Bartlett, Michael I. Jordan

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

Comments Published at NeurIPS 2022

2109.11978 2022-08-22 cs.RO cs.LG 62%

Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning

Nikita Rudin, David Hoeller, Philipp Reist, Marco Hutter

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

Comments CoRL 2021 Project website: : https://leggedrobotics.github.io/legged_gym/ Video: https://youtu.be/8sO7VS3q8d0

2104.00385 2022-08-09 cs.LG cs.RO 62%

Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures

Taisuke Kobayashi, Kenta Yoshizawa

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

Comments 23 pages, 12 figures

Journal ref ROBOMECH Journal, 2022

2102.00168 2022-08-09 cs.AI cs.RO 62%

Learning Skills to Navigate without a Master: A Sequential Multi-Policy Reinforcement Learning Algorithm

Ambedkar Dukkipati, Rajarshi Banerjee, Ranga Shaarad Ayyagari, Dhaval Parmar Udaybhai

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

Comments IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS): 2022

2208.02434 2022-08-05 cs.LG cs.RO 62%

Backward Imitation and Forward Reinforcement Learning via Bi-directional Model Rollouts

Yuxin Pan, Fangzhen Lin

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

Comments Accepted by IROS2022

2207.14140 2022-07-29 cs.LG cs.AI 62%

Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning

Jerin Paul Selvan, Pravin S. Game

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

Comments 5 pages, 7 figures, 3 tables

2202.00850 2022-07-26 cs.CV cs.LG cs.SD eess.AS eess.IV 62%

Active Audio-Visual Separation of Dynamic Sound Sources

Sagnik Majumder, Kristen Grauman

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

Comments Accepted to ECCV 2022

1. 模仿学习与强化学习 4134 篇

IQ-Learn: Inverse soft-Q Learning for Imitation

Teacher-student curriculum learning for reinforcement learning

Using Contrastive Samples for Identifying and Leveraging Possible Causal Relationships in Reinforcement Learning

Provable Safe Reinforcement Learning with Binary Feedback

Curriculum Reinforcement Learning using Optimal Transport via Gradual Domain Adaptation

Shapley Q-value: A Local Reward Approach to Solve Global Reward Games

Smooth Trajectory Collision Avoidance through Deep Reinforcement Learning

Meta-Reinforcement Learning with Self-Modifying Networks

Zero-Shot Policy Transfer with Disentangled Task Representation of Meta-Reinforcement Learning

Online Weighted Q-Ensembles for Reduced Hyperparameter Tuning in Reinforcement Learning

Reinforcement Learning Algorithms: An Overview and Classification

Reward Learning using Structural Motifs in Inverse Reinforcement Learning

Delayed Geometric Discounts: An Alternative Criterion for Reinforcement Learning

Robust Reinforcement Learning as a Stackelberg Game via Adaptively-Regularized Adversarial Training

Real-time Adversarial Perturbations against Deep Reinforcement Learning Policies: Attacks and Defenses

Towards Task-Prioritized Policy Composition

SoLo T-DIRL: Socially-Aware Dynamic Local Planner based on Trajectory-Ranked Deep Inverse Reinforcement Learning

Double Q-Learning for Citizen Relocation During Natural Hazards

A Survey on Large-Population Systems and Scalable Multi-Agent Reinforcement Learning

On Decentralizing Federated Reinforcement Learning in Multi-Robot Scenarios

A Deep Reinforcement Learning Strategy for UAV Autonomous Landing on a Platform

Generalized Reinforcement Learning: Experience Particles, Action Operator, Reinforcement Field, Memory Association, and Decision Concepts

Safety-Critical Learning of Robot Control with Temporal Logic Specifications

On the Theory of Reinforcement Learning with Once-per-Episode Feedback

Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning

Optimization Algorithm for Feedback and Feedforward Policies towards Robot Control Robust to Sensing Failures

Learning Skills to Navigate without a Master: A Sequential Multi-Policy Reinforcement Learning Algorithm

Backward Imitation and Forward Reinforcement Learning via Bi-directional Model Rollouts

Playing a 2D Game Indefinitely using NEAT and Reinforcement Learning

Active Audio-Visual Separation of Dynamic Sound Sources