机器人 / 具身智能 - arXivDaily 专题

2405.03878 2024-06-05 cs.LG cs.AI 62%

Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning

Aditya A. Ramesh, Kenny Young, Louis Kirsch, Jürgen Schmidhuber

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

Comments ICML 2024 version

2405.00516 2024-05-31 cs.LG cs.AI cs.CL 62%

Navigating WebAI: Training Agents to Complete Web Tasks with Large Language Models and Reinforcement Learning

Lucas-Andreï Thil, Mirela Popa, Gerasimos Spanakis

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

Comments ACM 2024, Avila Spain. 9 pages

Journal ref Proceedings of the 39th ACM/SIGAPP Symposium on Applied Computing, 2024

2405.19080 2024-05-30 cs.LG cs.AI 62%

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

Yu Luo, Tianying Ji, Fuchun Sun, Jianwei Zhang, Huazhe Xu, Xianyuan Zhan

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

2403.20016 2024-05-29 cs.RO cs.LG 62%

EnCoMP: Enhanced Covert Maneuver Planning with Adaptive Threat-Aware Visibility Estimation using Offline Reinforcement Learning

Jumman Hossain, Abu-Zaher Faridee, Nirmalya Roy, Jade Freeman, Timothy Gregory, Theron T. Trout

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

Comments Paper under review

2405.16739 2024-05-28 cs.LG cs.AI cs.SY eess.SY 62%

Oracle-Efficient Reinforcement Learning for Max Value Ensembles

Marcel Hussing, Michael Kearns, Aaron Roth, Sikata Bela Sengupta, Jessica Sorrell

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

2405.16390 2024-05-28 cs.AI cs.LG 62%

Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning

Shangding Gu, Bilgehan Sel, Yuhao Ding, Lu Wang, Qingwei Lin, Alois Knoll, Ming Jin

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

2405.16335 2024-05-28 cs.RO cs.LG 62%

RoboArm-NMP: a Learning Environment for Neural Motion Planning

Tom Jurgenson, Matan Sudry, Gal Avineri, Aviv Tamar

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

2402.13777 2024-05-28 cs.LG cs.AI 62%

Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions

Jiayu Chen, Bhargav Ganguly, Yang Xu, Yongsheng Mei, Tian Lan, Vaneet Aggarwal

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

Comments We restructured the paper and added more discussion

2205.10330 2024-05-28 cs.AI cs.LG 62%

A Review of Safe Reinforcement Learning: Methods, Theory and Applications

Shangding Gu, Long Yang, Yali Du, Guang Chen, Florian Walter, Jun Wang, Alois Knoll

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

2311.02198 2024-05-22 cs.LG cs.AI 62%

Imitation Bootstrapped Reinforcement Learning

Hengyuan Hu, Suvir Mirchandani, Dorsa Sadigh

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

2405.07603 2024-05-14 cs.RO cs.AI 62%

Reducing Risk for Assistive Reinforcement Learning Policies with Diffusion Models

Andrii Tytarenko

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

2405.03711 2024-05-08 cs.LG cs.AI cs.NE cs.SY eess.SY 62%

Guidance Design for Escape Flight Vehicle Using Evolution Strategy Enhanced Deep Reinforcement Learning

Xiao Hu, Tianshu Wang, Min Gong, Shaoshi Yang

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

Comments 13 pages, 13 figures, accepted to appear on IEEE Access, Mar. 2024

Journal ref IEEE Access, vol. 12, pp. 48210-48222, Mar. 2024

2405.02425 2024-05-07 cs.RO cs.AI 62%

Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning

Dhruva Tirumala, Markus Wulfmeier, Ben Moran, Sandy Huang, Jan Humplik, Guy Lever, Tuomas Haarnoja, Leonard Hasenclever, Arunkumar Byravan, Nathan Batchelor, Neil Sreendra, Kushal Patel, Marlon Gwira, Francesco Nori, Martin Riedmiller, Nicolas Heess

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

2404.15096 2024-05-01 cs.RO cs.LG 62%

Impedance Matching: Enabling an RL-Based Running Jump in a Quadruped Robot

Neil Guan, Shangqun Yu, Shifan Zhu, Donghyun Kim

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

Comments Accepted by Ubiquitous Robots 2024

2310.13639 2024-05-01 cs.LG cs.AI 62%

Contrastive Preference Learning: Learning from Human Feedback without RL

Joey Hejna, Rafael Rafailov, Harshit Sikchi, Chelsea Finn, Scott Niekum, W. Bradley Knox, Dorsa Sadigh

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

Comments ICLR 2024. Code released at https://github.com/jhejna/cpl

2307.02620 2024-04-22 cs.LG cs.AI 62%

Dynamic Observation Policies in Observation Cost-Sensitive Reinforcement Learning

Colin Bellinger, Mark Crowley, Isaac Tamblyn

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

Comments NeurIPS 2023 Workshop WANT

2310.17722 2024-04-17 cs.LG cs.AI cs.CL 62%

Large Language Models as Generalizable Policies for Embodied Tasks

Andrew Szot, Max Schwarzer, Harsh Agrawal, Bogdan Mazoure, Walter Talbott, Katherine Metcalf, Natalie Mackraz, Devon Hjelm, Alexander Toshev

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

2312.05332 2024-04-10 eess.SY cs.LG cs.RO cs.SY math.OC 62%

MPC-Inspired Reinforcement Learning for Verifiable Model-Free Control

Yiwen Lu, Zishuo Li, Yihan Zhou, Na Li, Yilin Mo

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

2404.05440 2024-04-09 cs.AI cs.LG 62%

Tree Search-Based Policy Optimization under Stochastic Execution Delay

David Valensi, Esther Derman, Shie Mannor, Gal Dalal

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

Comments Published in ICLR 2024

2403.00344 2024-04-02 cs.RO cs.LG 62%

Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Tasks

Takayuki Osa, Tatsuya Harada

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

Comments 7 pages, accepted for ICRA 2024

2403.15091 2024-03-25 cs.LG cs.AI cs.SY eess.SY 62%

Improved Long Short-Term Memory-based Wastewater Treatment Simulators for Deep Reinforcement Learning

Esmaeel Mohammadi, Daniel Ortiz-Arroyo, Mikkel Stokholm-Bjerregaard, Aviaja Anna Hansen, Petar Durdevic

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

2210.04688 2024-03-21 cs.LG cs.AI cs.CR 62%

BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets

Chen Gong, Zhou Yang, Yunpeng Bai, Junda He, Jieke Shi, Kecen Li, Arunesh Sinha, Bowen Xu, Xinwen Hou, David Lo, Tianhao Wang

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

Comments Accepted at IEEE S&P (Oakland) 2024

2210.10243 2024-03-18 cs.LG cs.AI 62%

CLUTR: Curriculum Learning via Unsupervised Task Representation Learning

Abdus Salam Azad, Izzeddin Gur, Jasper Emhoff, Nathaniel Alexis, Aleksandra Faust, Pieter Abbeel, Ion Stoica

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

Comments Preprint, Currently Under Review

2403.07916 2024-03-14 cs.AI cs.LG 62%

Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization

Philip Ndikum, Serge Ndikum

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

2403.03643 2024-03-08 cs.LG cs.AI 62%

A Survey on Applications of Reinforcement Learning in Spatial Resource Allocation

Di Zhang, Moyang Wang, Joseph Mango, Xiang Li, Xianrui Xu

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

2210.01282 2024-03-04 cs.LG cs.AI econ.EM stat.ML 62%

Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees

Siliang Zeng, Mingyi Hong, Alfredo Garcia

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

Comments This conference version of this paper refers to "Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees" in NeurIPS 2022

2402.17135 2024-02-28 cs.LG cs.AI 62%

Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings

Kevin Frans, Seohong Park, Pieter Abbeel, Sergey Levine

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

2310.04241 2024-02-19 cs.LG cs.AI 62%

Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison

Moritz Lange, Noah Krystiniak, Raphael C. Engelhardt, Wolfgang Konen, Laurenz Wiskott

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

Comments Accepted at LOD 2023

Journal ref Machine Learning, Optimization, and Data Science. LOD 2023. Lecture Notes in Computer Science, vol 14506. Springer, Cham

2402.09355 2024-02-15 cs.RO cs.AI 62%

Single-Reset Divide & Conquer Imitation Learning

Alexandre Chenu, Olivier Serris, Olivier Sigaud, Nicolas Perrin-Gilbert

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

2402.09290 2024-02-15 cs.LG cs.AI 62%

Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning

Michael Lanier, Ying Xu, Nathan Jacobs, Chongjie Zhang, Yevgeniy Vorobeychik

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

1. 模仿学习与强化学习 4131 篇

Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning

Navigating WebAI: Training Agents to Complete Web Tasks with Large Language Models and Reinforcement Learning

OMPO: A Unified Framework for RL under Policy and Dynamics Shifts

EnCoMP: Enhanced Covert Maneuver Planning with Adaptive Threat-Aware Visibility Estimation using Offline Reinforcement Learning

Oracle-Efficient Reinforcement Learning for Max Value Ensembles

Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning

RoboArm-NMP: a Learning Environment for Neural Motion Planning

Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions

A Review of Safe Reinforcement Learning: Methods, Theory and Applications

Imitation Bootstrapped Reinforcement Learning

Reducing Risk for Assistive Reinforcement Learning Policies with Diffusion Models

Guidance Design for Escape Flight Vehicle Using Evolution Strategy Enhanced Deep Reinforcement Learning

Learning Robot Soccer from Egocentric Vision with Deep Reinforcement Learning

Impedance Matching: Enabling an RL-Based Running Jump in a Quadruped Robot

Contrastive Preference Learning: Learning from Human Feedback without RL

Dynamic Observation Policies in Observation Cost-Sensitive Reinforcement Learning

Large Language Models as Generalizable Policies for Embodied Tasks

MPC-Inspired Reinforcement Learning for Verifiable Model-Free Control

Tree Search-Based Policy Optimization under Stochastic Execution Delay

Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Tasks

Improved Long Short-Term Memory-based Wastewater Treatment Simulators for Deep Reinforcement Learning

BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets

CLUTR: Curriculum Learning via Unsupervised Task Representation Learning

Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization

A Survey on Applications of Reinforcement Learning in Spatial Resource Allocation

Structural Estimation of Markov Decision Processes in High-Dimensional State Space with Finite-Time Guarantees

Unsupervised Zero-Shot Reinforcement Learning via Functional Reward Encodings

Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison

Single-Reset Divide & Conquer Imitation Learning

Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning