机器人 / 具身智能 - arXivDaily 专题

2505.22696 2025-05-30 cs.LG 57%

When Does Neuroevolution Outcompete Reinforcement Learning in Transfer Learning Tasks?

Eleni Nisioti, Joachim Winther Pedersen, Erwan Plantec, Milton L. Montero, Sebastian Risi

机构 * The Thørväld Group（索尔瓦尔德集团）； Inria Paris-Rocquencourt（巴黎-鲁克肯堡国家信息与自动化研究所）； Rajiv Gandhi University Doimukh（拉贾·甘地大学多伊穆克）； Tsinghua University（清华大学）； Palmer Research Laboratories（帕勒姆研究实验室）； The Kumquat Consortium（昆quat联盟）

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

2505.20889 2025-05-28 cs.AI 57%

Reinforcement Learning-based Sequential Route Recommendation for System-Optimal Traffic Assignment

Leizhen Wang, Peibo Duan, Cheng Lyu, Zhenliang Ma

机构 * Department of Data Science and Artificial Intelligence, Monash University（墨尔本大学数据科学与人工智能系）； Chair of Transportation Systems Engineering, Technical University of Munich（慕尼黑技术大学交通系统工程教授职位）； Department of Civil and Architectural Engineering, KTH Royal Institute of Technology（瑞典皇家理工学院土木与建筑工程系）

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

2502.02434 2025-05-27 cs.LG 57%

mPOLICE: Provable Enforcement of Multi-Region Affine Constraints in Deep Neural Networks

Mohammadmehdi Ataei, Hyunmin Cheong, Adrian Butscher

机构 * Autodesk Research（Autodesk研究）

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

2505.17218 2025-05-26 cs.AI 57%

Effective Reinforcement Learning for Reasoning in Language Models

Lianghuan Huang, Shuo Li, Sagnik Anupam, Insup Lee, Osbert Bastani

机构 * University of Pennsylvania（宾夕法尼亚大学）

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

2406.01309 2025-05-26 cs.NE cs.AI 57%

REvolve: Reward Evolution with Large Language Models using Human Feedback

Rishi Hazra, Alkis Sygkounas, Andreas Persson, Amy Loutfi, Pedro Zuidberg Dos Martires

机构 * Centre for Applied Autonomous Sensor Systems (AASS)（应用自主传感器系统中心）

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

Comments Published in ICLR 2025. Project page: https://rishihazra.github.io/REvolve

2405.13609 2025-05-26 cs.LG q-fin.CP quant-ph 57%

Tackling Decision Processes with Non-Cumulative Objectives using Reinforcement Learning

Maximilian Nägele, Jan Olle, Thomas Fösel, Remmy Zen, Florian Marquardt

机构 * Max Planck Institute for the Science of Light（马克斯·普朗克光科学研究所）； Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔兰根-纽伦堡弗里德里希-亚历山大大学）

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

2505.15211 2025-05-22 cs.RO 57%

GCNT: Graph-Based Transformer Policies for Morphology-Agnostic Reinforcement Learning

Yingbo Luo, Meibao Yao, Xueming Xiao

机构 * Jilin University（吉林大学）； Changchun University of Science and Technology（长春理工大学）

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

2505.12648 2025-05-20 cs.RO 57%

SafeMove-RL: A Certifiable Reinforcement Learning Framework for Dynamic Motion Constraints in Trajectory Planning

Tengfei Liu, Haoyang Zhong, Jiazheng Hu, Tan Zhang

机构 * Sino-German College of Intelligent Manufacturing, Shenzhen Technology University（深圳技术大学中德智能制造学院）； Faculty of Science and Technology, University of Macau（澳门大学科技学院）

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

2505.11858 2025-05-20 cs.RO 57%

Integrating Model-based Control and RL for Sim2Real Transfer of Tight Insertion Policies

Isidoros Marougkas, Dhruv Metha Ramesh, Joe H. Doerr, Edgar Granados, Aravind Sivaramakrishnan, Abdeslam Boularias, Kostas E. Bekris

机构 * Dept. of Computer Science, Rutgers University, NJ, USA（计算机科学系，新泽西州立大学）； Amazon.com Inc（亚马逊公司）； Rutgers University（新泽西州立大学）； Amazon Scholar（亚马逊学者）

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

2505.09979 2025-05-16 cs.RO 57%

Learning Diverse Natural Behaviors for Enhancing the Agility of Quadrupedal Robots

Huiqiao Fu, Haoyu Dong, Wentao Xu, Zhehao Zhou, Guizhou Deng, Kaiqiang Tang, Daoyi Dong, Chunlin Chen

机构 * Department of Control Science and Intelligent Engineering（控制科学与智能工程系）； School of Management and Engineering（管理与工程学院）； Australian Artificial Intelligence Institute（澳大利亚人工智能研究所）

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

2504.09192 2025-05-16 cs.LG 57%

Towards More Efficient, Robust, Instance-adaptive, and Generalizable Sequential Decision making

Zhiyong Wang

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

Comments Ph.D. Thesis

2505.08238 2025-05-14 cs.RO 57%

Motion Control of High-Dimensional Musculoskeletal Systems with Hierarchical Model-Based Planning

Yunyue Wei, Shanning Zhuang, Vincent Zhuang, Yanan Sui

机构 * Tsinghua University（清华大学）； Google DeepMind（谷歌DeepMind）

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

Comments Accepted by ICLR 2025

2505.02216 2025-05-13 cs.AI 57%

LLM-Guided Probabilistic Program Induction for POMDP Model Estimation

Aidan Curtis, Hao Tang, Thiago Veloso, Kevin Ellis, Joshua Tenenbaum, Tomás Lozano-Pérez, Leslie Pack Kaelbling

机构 * MIT（麻省理工学院）； Cornell University（康奈尔大学）

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

2407.13163 2025-05-13 cs.IR cs.AI 57%

ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems

Yi Zhang, Ruihong Qiu, Jiajun Liu, Sen Wang

机构 * The University of Queensland（昆士兰大学）； CSIRO DATA61

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

Comments CIKM 2024

2505.05548 2025-05-12 cs.RO cs.SY eess.SY 57%

Barrier Function Overrides For Non-Convex Fixed Wing Flight Control and Self-Driving Cars

Eric Squires, Phillip Odom, Zsolt Kira

机构 * Georgia Tech Research Institute（佐治亚理工学院研究 institute）； College of Computing at the Georgia Institute of Technology（佐治亚理工学院计算机学院）

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

Comments This work has been submitted to the IEEE for possible publication

2505.00671 2025-05-02 cs.RO cs.SY eess.SY 57%

Multi-Constraint Safe Reinforcement Learning via Closed-form Solution for Log-Sum-Exp Approximation of Control Barrier Functions

Chenggang Wang, Xinyi Wang, Yutong Dong, Lei Song, Xinping Guan

机构 * Shanghai Jiao Tong University（上海交通大学）； University of Michigan（密歇根大学）

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

2504.21433 2025-05-01 cs.AI 57%

NGENT: Next-Generation AI Agents Must Integrate Multi-Domain Abilities to Achieve Artificial General Intelligence

Zhicong Li, Hangyu Mao, Jiangjin Yin, Mingzhe Xing, Zhiwei Xu, Yuanxing Zhang, Yang Xiao

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

2209.04100 2025-04-29 cs.AI 57%

Task-Agnostic Learning to Accomplish New Tasks

Xianqi Zhang, Xingtao Wang, Xu Liu, Wenrui Wang, Xiaopeng Fan, Debin Zhao

机构 * Faculty of Computing, Harbin Institute of Technology（计算机学院，哈尔滨工业大学）； Peng Cheng Laboratory（鹏城实验室）； Harbin Institute of Technology Suzhou Research Institute（哈尔滨工业大学苏州研究院）

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

Comments 14 pages, 10 figures, Accepted by IEEE-TCDS

2504.15666 2025-04-23 cs.RO 57%

Symbolic Runtime Verification and Adaptive Decision-Making for Robot-Assisted Dressing

Yasmin Rafiq, Gricel Vázquez, Radu Calinescu, Sanja Dogramadzi, Robert M Hierons

机构 * Department of Computer Science（计算机科学系）； University of Manchester（曼彻斯特大学）； University of York（约克大学）； School of Electrical and Electronic Engineering（电子与电气工程学院）； The University of Sheffield（谢菲尔德大学）； School of Computer Science（计算机科学学院）

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

2502.06725 2025-04-23 cs.RO 57%

AgilePilot: DRL-Based Drone Agent for Real-Time Motion Planning in Dynamic Environments by Leveraging Object Detection

Roohan Ahmed Khan, Valerii Serpiva, Demetros Aschalew, Aleksey Fedoseev, Dzmitry Tsetserukou

机构 * Intelligent Space Robotics Laboratory（智能空间机器人实验室）； Center for Digital Engineering（数字工程中心）； Skolkovo Institute of Science and Technology（斯克尔科夫科学与技术研究所）

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

Comments Manuscript has been accepted at 2025 INTERNATIONAL CONFERENCE ON UNMANNED AIRCRAFT SYSTEMS (ICUAS)

2504.08195 2025-04-14 cs.MA cs.AI 57%

Graph Based Deep Reinforcement Learning Aided by Transformers for Multi-Agent Cooperation

Michael Elrod, Niloufar Mehrabi, Rahul Amin, Manveen Kaur, Long Cheng, Jim Martin, Abolfazl Razi

机构 * School of Computing, Clemson University（克莱姆森大学计算学院）； California State University, Los Angeles（加州州立大学洛杉矶分校）； Lincoln Laboratory, Massachusetts Institute of Technology（麻省理工学院林肯实验室）

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

Comments 6 pages, 7 figures, Accepted to the 2025 IEEE International Conference on Communications Workshops (ICC Workshops)

2504.05084 2025-04-08 cs.RO 57%

Speech-to-Trajectory: Learning Human-Like Verbal Guidance for Robot Motion

Eran Beeri Bamani, Eden Nissinman, Rotem Atari, Nevo Heimann Saadon, Avishai Sintov

机构 * School of Mechanical Engineering, Tel-Aviv University（特拉维夫大学机械工程学院）

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

2504.03938 2025-04-08 cs.RO 57%

Energy Efficient Planning for Repetitive Heterogeneous Tasks in Precision Agriculture

Shuangyu Xie, Ken Goldberg, Dezhen Song

机构 * University of California, Berkeley（加州大学伯克利分校）； Mohamed Bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）

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

Comments ICRA 2025

2504.03185 2025-04-07 cs.CL cs.AI 57%

Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents

Jaymari Chua, Chen Wang, Lina Yao

机构 * CSIRO’s Data61（联邦科学与工业研究组织数据61）； UNSW Sydney（新南威尔士大学悉尼分校）

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

2504.01915 2025-04-07 cs.NE cs.RO 57%

Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity

Lisa Coiffard, Paul Templier, Antoine Cully

机构 * Imperial College London（伦敦帝国学院）

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

2503.10419 2025-04-04 eess.SY cs.RO cs.SY 57%

A nonlinear real time capable motion cueing algorithm based on deep reinforcement learning

Hendrik Scheidel, Camilo Gonzalez, Houshyar Asadi, Tobias Bellmann, Andreas Seefried, Shady Mohamed, Saeid Nahavandi

机构 * Deutsches Zentrum für Luft- und Raumfahrt (DLR) German Aerospace Center（德国航空航天中心）； Institute for Intelligent Systems Research and Innovation, Deakin University（迪肯大学智能系统研究与创新学院）； Institute of Flight Systems, German Aerospace Center（德国航空航天中心飞行系统研究所）； Swinburne University（斯威本科技大学）

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

2410.08896 2025-04-04 cs.LG 57%

MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL

Claas A Voelcker, Marcel Hussing, Eric Eaton, Amir-massoud Farahmand, Igor Gilitschenski

机构 * University of Toronto（多伦多大学）； Vector Institute（向量研究所）； University of Pennsylvania（宾夕法尼亚大学）； Polytechnique Montréal（蒙特利尔理工学院）； Mila – Quebec AI Institute（米拉-魁北克人工智能研究所）

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

2503.23486 2025-04-01 cs.AI 57%

A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior

Nikil Jayasuriya, Deshan Sumanathilaka

机构 * Informatics Institute of Technology（信息技术学院）； Swansea University（斯旺西大学）

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

Comments 6 pages, 2 figures, 1 table

2503.18366 2025-03-25 cs.RO 57%

Reinforcement Learning for Adaptive Planner Parameter Tuning: A Perspective on Hierarchical Architecture

Lu Wangtao, Wei Yufei, Xu Jiadong, Jia Wenhao, Li Liang, Xiong Rong, Wang Yue

机构 * Zhejiang University（浙江大学）； Zhejiang University of Technology（浙江工业大学）

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

2503.17615 2025-03-25 cs.RO physics.ins-det 57%

Feature Selection Based on Reinforcement Learning and Hazard State Classification for Magnetic Adhesion Wall-Climbing Robots

Zhen Ma, He Xu, Jielong Dou, Yi Qin, Xueyu Zhang

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

Comments 21 pages, 11 figures, manuscript for Journal of Autonomous Robots

1. 模仿学习与强化学习 4134 篇

When Does Neuroevolution Outcompete Reinforcement Learning in Transfer Learning Tasks?

Reinforcement Learning-based Sequential Route Recommendation for System-Optimal Traffic Assignment

mPOLICE: Provable Enforcement of Multi-Region Affine Constraints in Deep Neural Networks

Effective Reinforcement Learning for Reasoning in Language Models

REvolve: Reward Evolution with Large Language Models using Human Feedback

Tackling Decision Processes with Non-Cumulative Objectives using Reinforcement Learning

GCNT: Graph-Based Transformer Policies for Morphology-Agnostic Reinforcement Learning

SafeMove-RL: A Certifiable Reinforcement Learning Framework for Dynamic Motion Constraints in Trajectory Planning

Integrating Model-based Control and RL for Sim2Real Transfer of Tight Insertion Policies

Learning Diverse Natural Behaviors for Enhancing the Agility of Quadrupedal Robots

Towards More Efficient, Robust, Instance-adaptive, and Generalizable Sequential Decision making

Motion Control of High-Dimensional Musculoskeletal Systems with Hierarchical Model-Based Planning

LLM-Guided Probabilistic Program Induction for POMDP Model Estimation

ROLeR: Effective Reward Shaping in Offline Reinforcement Learning for Recommender Systems

Barrier Function Overrides For Non-Convex Fixed Wing Flight Control and Self-Driving Cars

Multi-Constraint Safe Reinforcement Learning via Closed-form Solution for Log-Sum-Exp Approximation of Control Barrier Functions

NGENT: Next-Generation AI Agents Must Integrate Multi-Domain Abilities to Achieve Artificial General Intelligence

Task-Agnostic Learning to Accomplish New Tasks

Symbolic Runtime Verification and Adaptive Decision-Making for Robot-Assisted Dressing

AgilePilot: DRL-Based Drone Agent for Real-Time Motion Planning in Dynamic Environments by Leveraging Object Detection

Graph Based Deep Reinforcement Learning Aided by Transformers for Multi-Agent Cooperation

Speech-to-Trajectory: Learning Human-Like Verbal Guidance for Robot Motion

Energy Efficient Planning for Repetitive Heterogeneous Tasks in Precision Agriculture

Learning Natural Language Constraints for Safe Reinforcement Learning of Language Agents

Overcoming Deceptiveness in Fitness Optimization with Unsupervised Quality-Diversity

A nonlinear real time capable motion cueing algorithm based on deep reinforcement learning

MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL

A Systematic Decade Review of Trip Route Planning with Travel Time Estimation based on User Preferences and Behavior

Reinforcement Learning for Adaptive Planner Parameter Tuning: A Perspective on Hierarchical Architecture

Feature Selection Based on Reinforcement Learning and Hazard State Classification for Magnetic Adhesion Wall-Climbing Robots