机器人 / 具身智能 - arXivDaily 专题

2310.20663 2023-11-01 cs.LG cs.AI 62%

Offline RL with Observation Histories: Analyzing and Improving Sample Complexity

Joey Hong, Anca Dragan, Sergey Levine

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

Comments 21 pages, 4 figures

2310.19927 2023-11-01 cs.LG cs.AI 62%

Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms

Shenao Zhang, Boyi Liu, Zhaoran Wang, Tuo Zhao

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 2023

2307.14993 2023-10-30 cs.AI cs.LG 62%

Thinker: Learning to Plan and Act

Stephen Chung, Ivan Anokhin, David Krueger

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

Comments 38 pages

2306.14884 2023-10-30 cs.LG cs.AI 62%

Learning to Modulate pre-trained Models in RL

Thomas Schmied, Markus Hofmarcher, Fabian Paischer, Razvan Pascanu, Sepp Hochreiter

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

Comments 10 pages (+ references and appendix), Code: https://github.com/ml-jku/L2M

2212.04407 2023-10-26 cs.LG cs.AI 62%

Dynamic Decision Frequency with Continuous Options

Amirmohammad Karimi, Jun Jin, Jun Luo, A. Rupam Mahmood, Martin Jagersand, Samuele Tosatto

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

Comments Appears in the Proceedings of the 2023 International Conference on Intelligent Robots and Systems (IROS). Source code at https://github.com/amir-karimi96/continuous-time-continuous-option-policy-gradient.git

2310.13295 2023-10-23 cs.RO cs.AI 62%

PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning

Wenhao Yu, Jie Peng, Quecheng Qiu, Hanyu Wang, Lu Zhang, Jianmin Ji

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

2306.15228 2023-10-23 cs.RO cs.AI 62%

IIFL: Implicit Interactive Fleet Learning from Heterogeneous Human Supervisors

Gaurav Datta, Ryan Hoque, Anrui Gu, Eugen Solowjow, Ken Goldberg

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

Comments CoRL 2023

2210.13623 2023-10-20 cs.AI cs.CL cs.LG cs.SD eess.AS 62%

Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook

Baihan Lin

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

Comments To appear in Expert Systems with Applications. Accompanying INTERSPEECH 2022 Tutorial on the same topic. Including latest advancements in large language models (LLMs)

2302.13137 2023-10-18 cs.RO cs.AI 62%

A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors

Shangding Gu, Alap Kshirsagar, Yali Du, Guang Chen, Jan Peters, Alois Knoll

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

2303.03811 2023-10-17 cs.LG cs.AI 62%

Environment Transformer and Policy Optimization for Model-Based Offline Reinforcement Learning

Pengqin Wang, Meixin Zhu, Shaojie Shen

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

Comments ICRA2024

2310.09997 2023-10-17 cs.AI cs.LG cs.SY eess.SY 62%

Forecaster: Towards Temporally Abstract Tree-Search Planning from Pixels

Thomas Jiralerspong, Flemming Kondrup, Doina Precup, Khimya Khetarpal

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

2305.16317 2023-10-17 cs.LG cs.AI 62%

Parallel Sampling of Diffusion Models

Andy Shih, Suneel Belkhale, Stefano Ermon, Dorsa Sadigh, Nima Anari

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

Comments 37th Conference on Neural Information Processing Systems

2203.13424 2023-10-17 cs.LG cs.AI cs.NE 62%

Dealing with Sparse Rewards Using Graph Neural Networks

Matvey Gerasyov, Ilya Makarov

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

Journal ref IEEE Access, vol. 11, pp. 89180-89187, 2023

2310.07899 2023-10-13 cs.AI cs.RO 62%

RoboCLIP: One Demonstration is Enough to Learn Robot Policies

Sumedh A Sontakke, Jesse Zhang, Sébastien M. R. Arnold, Karl Pertsch, Erdem Bıyık, Dorsa Sadigh, Chelsea Finn, Laurent Itti

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

2310.03161 2023-10-06 cs.LG cs.AI 62%

Neural architecture impact on identifying temporally extended Reinforcement Learning tasks

Victor Vadakechirayath George

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

Comments Master's thesis at Albert-Ludwigs-University, Freiburg Faculty of Engineering, Department of Computer Science Chair for Machine Learning. Advisor: Raghu Rajan, Examiners: Prof. Dr. Frank Hutter, Prof. Dr. Thomas Brox

2304.04066 2023-10-02 eess.SY cs.LG cs.RO cs.SY 62%

Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach

Liqun Zhao, Konstantinos Gatsis, Antonis Papachristodoulou

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

Comments Accepted by IEEE CDC 2023

2309.16074 2023-09-29 cs.RO cs.LG 62%

Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning

Feiyang Wu, Zhaoyuan Gu, Hanran Wu, Anqi Wu, Ye Zhao

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

2303.08690 2023-09-28 cs.LG cs.AI 62%

Replay Buffer with Local Forgetting for Adapting to Local Environment Changes in Deep Model-Based Reinforcement Learning

Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Harm van Seijen, Sarath Chandar

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

2309.14727 2023-09-27 eess.SY cs.AI cs.LG cs.SY 62%

Effective Multi-Agent Deep Reinforcement Learning Control with Relative Entropy Regularization

Chenyang Miao, Yunduan Cui, Huiyun Li, Xinyu Wu

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

2309.14096 2023-09-26 cs.LG cs.RO 62%

Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning

Pascal Klink, Florian Wolf, Kai Ploeger, Jan Peters, Joni Pajarinen

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

2210.05178 2023-09-26 cs.RO cs.LG 62%

Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials

Aviral Kumar, Anikait Singh, Frederik Ebert, Mitsuhiko Nakamoto, Yanlai Yang, Chelsea Finn, Sergey Levine

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

2309.11089 2023-09-21 eess.SY cs.AI cs.LG cs.SY 62%

Practical Probabilistic Model-based Deep Reinforcement Learning by Integrating Dropout Uncertainty and Trajectory Sampling

Wenjun Huang, Yunduan Cui, Huiyun Li, Xinyu Wu

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

2305.16979 2023-09-21 cs.AI cs.LG 62%

Adaptive PD Control using Deep Reinforcement Learning for Local-Remote Teleoperation with Stochastic Time Delays

Luc McCutcheon, Saber Fallah

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

Comments 7 pages + 1 references, 4 figures

2302.06692 2023-09-18 cs.LG cs.AI cs.CL 62%

Guiding Pretraining in Reinforcement Learning with Large Language Models

Yuqing Du, Olivia Watkins, Zihan Wang, Cédric Colas, Trevor Darrell, Pieter Abbeel, Abhishek Gupta, Jacob Andreas

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

Comments ICML 2023

2309.02976 2023-09-08 cs.RO cs.LG 62%

Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models

Pierre Schumacher, Thomas Geijtenbeek, Vittorio Caggiano, Vikash Kumar, Syn Schmitt, Georg Martius, Daniel F. B. Haeufle

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

2308.14919 2023-09-04 cs.LG cs.AI 62%

On Reward Structures of Markov Decision Processes

Falcon Z. Dai

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

Comments This PhD thesis draws heavily from arXiv:1907.02114 and arXiv:2002.06299; minor edits

2308.12438 2023-08-25 cs.LG cs.AI cs.SE 62%

Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges

Ahmed Haj Yahmed, Altaf Allah Abbassi, Amin Nikanjam, Heng Li, Foutse Khomh

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

Comments Accepted for publication in The International Conference on Software Maintenance and Evolution (ICSME 2023)

2308.12270 2023-08-24 cs.LG cs.AI 62%

Language Reward Modulation for Pretraining Reinforcement Learning

Ademi Adeniji, Amber Xie, Carmelo Sferrazza, Younggyo Seo, Stephen James, Pieter Abbeel

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

Comments Code available at https://github.com/ademiadeniji/lamp

2308.10797 2023-08-23 cs.LG cs.AI 62%

Stabilizing Unsupervised Environment Design with a Learned Adversary

Ishita Mediratta, Minqi Jiang, Jack Parker-Holder, Michael Dennis, Eugene Vinitsky, Tim Rocktäschel

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

Comments CoLLAs 2023 - Oral; Second and third authors contributed equally

2306.06236 2023-08-22 cs.MA cs.LG cs.RO 62%

iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning

Xiyang Wu, Rohan Chandra, Tianrui Guan, Amrit Singh Bedi, Dinesh Manocha

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

1. 模仿学习与强化学习 4131 篇

Offline RL with Observation Histories: Analyzing and Improving Sample Complexity

Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms

Thinker: Learning to Plan and Act

Learning to Modulate pre-trained Models in RL

Dynamic Decision Frequency with Continuous Options

PathRL: An End-to-End Path Generation Method for Collision Avoidance via Deep Reinforcement Learning

IIFL: Implicit Interactive Fleet Learning from Heterogeneous Human Supervisors

Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook

A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors

Environment Transformer and Policy Optimization for Model-Based Offline Reinforcement Learning

Forecaster: Towards Temporally Abstract Tree-Search Planning from Pixels

Parallel Sampling of Diffusion Models

Dealing with Sparse Rewards Using Graph Neural Networks

RoboCLIP: One Demonstration is Enough to Learn Robot Policies

Neural architecture impact on identifying temporally extended Reinforcement Learning tasks

Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach

Infer and Adapt: Bipedal Locomotion Reward Learning from Demonstrations via Inverse Reinforcement Learning

Replay Buffer with Local Forgetting for Adapting to Local Environment Changes in Deep Model-Based Reinforcement Learning

Effective Multi-Agent Deep Reinforcement Learning Control with Relative Entropy Regularization

Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning

Pre-Training for Robots: Offline RL Enables Learning New Tasks from a Handful of Trials

Practical Probabilistic Model-based Deep Reinforcement Learning by Integrating Dropout Uncertainty and Trajectory Sampling

Adaptive PD Control using Deep Reinforcement Learning for Local-Remote Teleoperation with Stochastic Time Delays

Guiding Pretraining in Reinforcement Learning with Large Language Models

Natural and Robust Walking using Reinforcement Learning without Demonstrations in High-Dimensional Musculoskeletal Models

On Reward Structures of Markov Decision Processes

Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challenges

Language Reward Modulation for Pretraining Reinforcement Learning

Stabilizing Unsupervised Environment Design with a Learned Adversary

iPLAN: Intent-Aware Planning in Heterogeneous Traffic via Distributed Multi-Agent Reinforcement Learning