机器人 / 具身智能 - arXivDaily 专题

2205.10787 2022-05-24 cs.LG cs.AI 62%

A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning

Zhi Wang, Chunlin Chen, Daoyi Dong

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

Comments Manuscript accepted by IEEE Transactions on Cybernetics, 2022, DOI: DOI: 10.1109/TCYB.2022.3170485

2205.10464 2022-05-24 cs.AI cs.LO cs.RO 62%

Synthesis from Satisficing and Temporal Goals

Suguman Bansal, Lydia Kavraki, Moshe Y. Vardi, Andrew Wells

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

2205.08013 2022-05-23 cs.LG cs.CV 62%

Continual learning on 3D point clouds with random compressed rehearsal

Maciej Zamorski, Michał Stypułkowski, Konrad Karanowski, Tomasz Trzciński, Maciej Zięba

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

Comments 10 pages, 3 figures

2205.09448 2022-05-20 cs.AI cs.CV 62%

Image Augmentation Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes

Zheng Fang, Biao Zhao, Guizhong Liu

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

2111.08575 2022-05-19 cs.RO cs.CV 62%

GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving

Raphael Chekroun, Marin Toromanoff, Sascha Hornauer, Fabien Moutarde

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

2106.13970 2022-05-16 cs.LG cs.AI 62%

Intrinsically Motivated Self-supervised Learning in Reinforcement Learning

Yue Zhao, Chenzhuang Du, Hang Zhao, Tiejun Li

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

2112.03482 2022-05-13 cs.LG cs.AI cs.HC 62%

Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft

Vinicius G. Goecks, Nicholas Waytowich, David Watkins-Valls, Bharat Prakash

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

Comments Submitted to the AAAI 2022 Spring Symposium on Machine Learning and Knowledge Engineering for Hybrid Intelligence (AAAI-MAKE 2022)

2205.05230 2022-05-12 cs.LG cs.AI 62%

Developing cooperative policies for multi-stage reinforcement learning tasks

Jordan Erskine, Chris Lehnert

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

Comments This paper supersedes the rejected paper "Developing cooperative policies for multi-stage tasks". arXiv admin note: substantial text overlap with arXiv:2007.00203

2202.11296 2022-04-25 cs.LG cs.AI 62%

Reinforcement Learning in Practice: Opportunities and Challenges

Yuxi Li

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

2204.08573 2022-04-20 cs.LG cs.RO 62%

Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models

Ali Ghadirzadeh, Petra Poklukar, Karol Arndt, Chelsea Finn, Ville Kyrki, Danica Kragic, Mårten Björkman

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: substantial text overlap with arXiv:2007.13134

2203.13733 2022-04-13 cs.RO cs.LG 62%

Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning

Seyed Kamyar Seyed Ghasemipour, Daniel Freeman, Byron David, Shixiang Shane Gu, Satoshi Kataoka, Igor Mordatch

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

Comments Accompanying project webpage can be found at: https://sites.google.com/view/learning-direct-assembly

2112.05923 2022-04-05 cs.LG cs.AI cs.DC 62%

ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning

Xiao-Yang Liu, Zechu Li, Zhuoran Yang, Jiahao Zheng, Zhaoran Wang, Anwar Walid, Jian Guo, Michael I. Jordan

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

Comments 9 pages, 7 figures

Journal ref Deep Reinforcement Learning Workshop, NeurIPS 2021

2010.04605 2022-04-01 cs.LG cs.AI cs.NE 62%

Instance Weighted Incremental Evolution Strategies for Reinforcement Learning in Dynamic Environments

Zhi Wang, Chunlin Chen, Daoyi Dong

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, 2022, DOI: 10.1109/TNNLS.2022.3160173

2203.07454 2022-03-16 cs.LG cs.AI 62%

L2Explorer: A Lifelong Reinforcement Learning Assessment Environment

Erik C. Johnson, Eric Q. Nguyen, Blake Schreurs, Chigozie S. Ewulum, Chace Ashcraft, Neil M. Fendley, Megan M. Baker, Alexander New, Gautam K. Vallabha

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

Comments 10 Pages submitted to AAAI AI for Open Worlds Symposium 2022

2109.07723 2022-03-10 cs.LG cs.AI 62%

Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patterns

Prasanth Buddareddygari, Travis Zhang, Yezhou Yang, Yi Ren

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

Comments 7 pages, 4 figures; Accepted at ICRA 2022

2203.04272 2022-03-09 cs.LG cs.AI stat.ME 62%

Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Models

Vincent Lim, Ellen Novoseller, Jeffrey Ichnowski, Huang Huang, Ken Goldberg

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

Comments 15 pages, 3 figures

2203.02857 2022-03-08 cs.LG cs.RO cs.SY eess.SY 62%

Leveraging Reward Gradients For Reinforcement Learning in Differentiable Physics Simulations

Sean Gillen, Katie Byl

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

2203.02844 2022-03-08 cs.LG cs.AI cs.MA 62%

Recursive Reasoning Graph for Multi-Agent Reinforcement Learning

Xiaobai Ma, David Isele, Jayesh K. Gupta, Kikuo Fujimura, Mykel J. Kochenderfer

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

Comments AAAI 2022

2109.05604 2022-03-08 cs.RO cs.LG 62%

Direct Random Search for Fine Tuning of Deep Reinforcement Learning Policies

Sean Gillen, Asutay Ozmen, Katie Byl

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

Comments Under Review

2203.00368 2022-03-02 cs.RO cs.LG 62%

Explaining a Deep Reinforcement Learning Docking Agent Using Linear Model Trees with User Adapted Visualization

Vilde B. Gjærum, Inga Strümke, Ole Andreas Alsos, Anastasios M. Lekkas

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

2202.09982 2022-02-23 cs.CV cs.LG 62%

Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning

Zhecheng Yuan, Guozheng Ma, Yao Mu, Bo Xia, Bo Yuan, Xueqian Wang, Ping Luo, Huazhe Xu

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

2202.10057 2022-02-22 cs.LG cs.AI 62%

CCPT: Automatic Gameplay Testing and Validation with Curiosity-Conditioned Proximal Trajectories

Alessandro Sestini, Linus Gisslén, Joakim Bergdahl, Konrad Tollmar, Andrew D. Bagdanov

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

2202.09646 2022-02-22 cs.AI cs.RO cs.SY eess.SY 62%

Navigating Conceptual Space; A new take on Artificial General Intelligence

Per R. Leikanger

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

Comments Featured in the conference of Artificial General Intelligence 2021. Part of the Lecture Notes in Computer Science book series (LNCS, volume 13154) and Lecture Notes in Artificial Intelligence book sub series (LNAI, volume 13154)

Journal ref Electronic ISSN 1611-3349 Lecture Notes in Computer Science 2021

2202.09644 2022-02-22 cs.RO cs.AI 62%

Multi-task Safe Reinforcement Learning for Navigating Intersections in Dense Traffic

Yuqi Liu, Qichao Zhang, Dongbin Zhao

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

1907.09470 2022-02-18 cs.LG cs.AI cs.CR stat.ML 62%

Characterizing Attacks on Deep Reinforcement Learning

Xinlei Pan, Chaowei Xiao, Warren He, Shuang Yang, Jian Peng, Mingjie Sun, Jinfeng Yi, Zijiang Yang, Mingyan Liu, Bo Li, Dawn Song

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

Comments AAMAS 2022, 13 pages, 6 figures

2201.13388 2022-02-01 cs.RO cs.LG stat.ML 62%

Compositional Multi-Object Reinforcement Learning with Linear Relation Networks

Davide Mambelli, Frederik Träuble, Stefan Bauer, Bernhard Schölkopf, Francesco Locatello

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

2109.04150 2022-02-01 cs.LG cs.RO 62%

Self-supervised Reinforcement Learning with Independently Controllable Subgoals

Andrii Zadaianchuk, Georg Martius, Fanny Yang

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

2201.08896 2022-01-25 cs.LG cs.AI 62%

Environment Generation for Zero-Shot Compositional Reinforcement Learning

Izzeddin Gur, Natasha Jaques, Yingjie Miao, Jongwook Choi, Manoj Tiwari, Honglak Lee, Aleksandra Faust

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

Comments Published in NeurIPS 2021

2201.07958 2022-01-21 cs.LG cs.AI 62%

Recursive Constraints to Prevent Instability in Constrained Reinforcement Learning

Jaeyoung Lee, Sean Sedwards, Krzysztof Czarnecki

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

Comments Accepted at 1st Multi-Objective Decision Making Workshop (MODeM 2021). Cite as: Jaeyoung Lee, Sean Sedwards and Krzysztof Czarnecki. (2021). Recursive constraints to prevent instability in constrained reinforcement learning. In: Proc. 1st Multi-Objective Decision Making Workshop (MODeM 2021), Hayes, Mannion, Vamplew (eds). Online at http://modem2021.cs.nuigalway.ie

2112.04216 2022-01-11 cs.LG cs.RO 62%

Specializing Versatile Skill Libraries using Local Mixture of Experts

Onur Celik, Dongzhuoran Zhou, Ge Li, Philipp Becker, Gerhard Neumann

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

Comments published at CoRL 2021 London

1. 模仿学习与强化学习 4115 篇

A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning

Synthesis from Satisficing and Temporal Goals

Continual learning on 3D point clouds with random compressed rehearsal

Image Augmentation Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes

GRI: General Reinforced Imitation and its Application to Vision-Based Autonomous Driving

Intrinsically Motivated Self-supervised Learning in Reinforcement Learning

Combining Learning from Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft

Developing cooperative policies for multi-stage reinforcement learning tasks

Reinforcement Learning in Practice: Opportunities and Challenges

Training and Evaluation of Deep Policies using Reinforcement Learning and Generative Models

Blocks Assemble! Learning to Assemble with Large-Scale Structured Reinforcement Learning

ElegantRL-Podracer: Scalable and Elastic Library for Cloud-Native Deep Reinforcement Learning

Instance Weighted Incremental Evolution Strategies for Reinforcement Learning in Dynamic Environments

L2Explorer: A Lifelong Reinforcement Learning Assessment Environment

Targeted Attack on Deep RL-based Autonomous Driving with Learned Visual Patterns

Policy-Based Bayesian Experimental Design for Non-Differentiable Implicit Models

Leveraging Reward Gradients For Reinforcement Learning in Differentiable Physics Simulations

Recursive Reasoning Graph for Multi-Agent Reinforcement Learning

Direct Random Search for Fine Tuning of Deep Reinforcement Learning Policies

Explaining a Deep Reinforcement Learning Docking Agent Using Linear Model Trees with User Adapted Visualization

Don't Touch What Matters: Task-Aware Lipschitz Data Augmentation for Visual Reinforcement Learning

CCPT: Automatic Gameplay Testing and Validation with Curiosity-Conditioned Proximal Trajectories

Navigating Conceptual Space; A new take on Artificial General Intelligence

Multi-task Safe Reinforcement Learning for Navigating Intersections in Dense Traffic

Characterizing Attacks on Deep Reinforcement Learning

Compositional Multi-Object Reinforcement Learning with Linear Relation Networks

Self-supervised Reinforcement Learning with Independently Controllable Subgoals

Environment Generation for Zero-Shot Compositional Reinforcement Learning

Recursive Constraints to Prevent Instability in Constrained Reinforcement Learning

Specializing Versatile Skill Libraries using Local Mixture of Experts