机器人 / 具身智能 - arXivDaily 专题

2403.10723 2026-02-17 eess.SY cs.SY 50%

Towards Dynamic Quadrupedal Gaits: A Symmetry-Guided RL Hierarchy Enables Free Gait Transitions at Varying Speeds

迈向动态四足步态：基于对称性的强化学习层次结构实现自由步态转换于不同速度下

Jiayu Ding, Xulin Chen, Garret E. Katz, Zhenyu Gan

专题命中模仿学习与强化学习：robotic(abstract)

AI总结本文提出基于对称性的强化学习方法，实现四足机器人在不同速度下的自由步态转换，提升步态适应性。

2601.16648 2026-01-26 eess.SY cs.SY 50%

A Cognitive Framework for Autonomous Agents: Toward Human-Inspired Design

自主代理的认知框架：迈向人机协同设计

Francesco Guidi, Jingfeng Shan, Mehrdad Saeidi, Enrico Testi, Elia Favarelli, Andrea Giorgetti, Davide Dardari, Alberto Zanella, Giorgio Li Pira, Francesca Starita, Anna Guerra

专题命中模仿学习与强化学习：navigation(abstract)

AI总结本文提出一种融合经典条件反射与工具性学习的强化学习框架，以提升自主系统在未知环境中的决策效率与合作能力。

2601.16061 2026-01-23 eess.SY cs.SY 50%

Dynamic Tactile Sensing System and Soft Actor Critic Reinforcement Learning for Inclusion Characterization

动态触觉传感系统与软演员评论强化学习用于包容体表征

John Bannan, Nazia Rahman, Chang-Hee Won

专题命中模仿学习与强化学习：robotic(abstract)

AI总结本文提出一种结合机器人触觉传感与软演员评论强化学习的动态触觉传感系统，用于精准定位和表征嵌入的包容体，实验表明其在尺寸估计精度上优于人工操作。

2601.09215 2026-01-15 cs.CL 50%

UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning

UserLM-R1: 通过多奖励强化学习建模人类推理在用户语言模型中的应用

Feng Zhang, Shijia Li, Chunmao Zhang, Zhanyu Ma, Jun Xu, Jiuchong Gao, Jinghua Hao, Renqing He, Jingwen Xu, Han Liu

机构 * Meituan（美团）； Peking University（北京大学）； Beijing University of Posts and Telecommunications（北京邮电大学）； University of Chinese Academy of Sciences（中国科学院大学）； Dalian University of Technology（大连理工大学）

专题命中模仿学习与强化学习：manipulation(abstract)

AI总结 UserLM-R1通过多奖励强化学习和动态目标驱动策略，提升用户语言模型在跨领域和对抗性场景中的推理与策略能力。

2512.17841 2025-12-22 cs.CE cs.SY eess.SY 50%

NeuRehab: A Reinforcement Learning and Spiking Neural Network-Based Rehab Automation Framework

NeuRehab：一种基于强化学习和脉冲神经网络的康复自动化框架

Phani Pavan Kambhampati, Chainesh Gautam, Jagan Palaniswamy, Madhav Rao

专题命中模仿学习与强化学习：robotic(abstract)

AI总结 NeuRehab通过结合强化学习和脉冲神经网络，实现康复自动化框架，优化功耗和延迟，提升神经形态部署性能。

Comments 18 pages, 22 figures, 3 tables, for submission to IOP Neuromorphic Computing and Engineering

2512.07783 2025-12-09 cs.CL 50%

On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models

在预训练、中训练和强化学习对推理语言模型的相互作用中

Charlie Zhang, Graham Neubig, Xiang Yue

机构 * Carnegie Mellon University, Language Technologies Institute（卡内基梅隆大学，语言技术研究所）

专题命中模仿学习与强化学习：manipulation(abstract)

AI总结研究探讨了预训练、中训练和强化学习在推理语言模型中的相互作用，发现RL需预训练留有余地才能提升能力，中训练提升性能，过程级奖励提高推理准确性。

2512.06645 2025-12-09 cs.MA 50%

Analyzing Collision Rates in Large-Scale Mixed Traffic Control via Multi-Agent Reinforcement Learning

通过多智能体强化学习分析大规模混合交通控制中的碰撞率

Muyang Fan

专题命中模仿学习与强化学习：robotic(abstract)

AI总结本研究通过多智能体强化学习分析大规模混合交通控制中的碰撞率影响因素，探讨交通密度、信号协调和转向策略对碰撞风险的作用，为提升交通系统安全性和效率提供理论支持。

2512.06095 2025-12-09 cond-mat.str-el 50%

Comparative Analysis of Autonomous and Systematic Control Strategies for Hole-Doped Hubbard Clusters: Reinforcement Learning versus Physics-Guided Design

自适应与系统化控制策略在掺空Hubbard簇中的比较分析：强化学习与物理引导设计

Shivanshu Dwivedi, Kalum Palandage

专题命中模仿学习与强化学习：navigation(abstract)

AI总结本文比较了自主强化学习与物理引导设计在掺空Hubbard簇中的表现，证明自主RL在优化和策略发现中具有高效性和竞争力。

2502.20953 2025-12-05 eess.SY cs.SY 50%

Optimality and Suboptimality of MPPI Control in Stochastic and Deterministic Settings

在随机和确定性设置中MPPI控制的最优性与次优性质

Hannes Homburger, Florian Messerer, Moritz Diehl, Johannes Reuter

专题命中模仿学习与强化学习：robotics(abstract)

AI总结本文研究了MPPI控制在确定性系统中的次优性质，并通过调整超参数来调节其性能。

Comments 6 pages, 3 figures, submitted to LCSS with CDC25 option

2511.17653 2025-11-25 math.GM 50%

MARL-CC: A Mathematical Framework forMulti-Agent Reinforcement Learning in ConnectedAutonomous Vehicles: Addressing Nonlinearity,Partial Observability, and Credit Assignment forOptimal Control

MARL-CC：多智能体强化学习在连接自动驾驶车辆中的数学框架：解决非线性、部分可观测性和信用分配以实现最优控制

Mazyar Taghavi, Javad Vahidi

专题命中模仿学习与强化学习：robotics(abstract)

AI总结 MARL-CC提出了一种统一的数学框架，通过整合微分几何控制、贝叶斯推断和夏普利值信用分配，解决多智能体强化学习中的非线性、部分可观测性和信用分配问题，提升收敛速度和协同效率。

2104.12145 2025-11-25 physics.optics 50%

LLM4Laser: Large Language Models Automate the Design of Lasers

LLM4Laser: 利用大语言模型自动化激光器设计

Renjie Li, Ceyao Zhang, Sixuan Mao, Xiyuan Zhou, Feng Yin, Sergios Theodoridis, Zhaoyu Zhang

专题命中模仿学习与强化学习：robotics(abstract)

AI总结本文提出利用大语言模型实现激光器设计自动化，通过对话生成仿真和强化学习代码，实现从概念到算法的全流程自动化设计。

Comments 14 pages, 10 figures

2511.17304 2025-11-24 q-fin.CP 50%

Law-Strength Frontiers and a No-Free-Lunch Result for Law-Seeking Reinforcement Learning on Volatility Law Manifolds

法律强度前沿与在波动率法律流形上寻求法律的强化学习的无免费午餐结果

Jian'an Zhang

专题命中模仿学习与强化学习：world model(abstract)

AI总结本文研究了在波动率法律流形上强化学习的法律强度权衡及无免费午餐问题，通过实验揭示法律寻求RL在波动率建模中的局限性。

Comments 61 pages, 14 figures

2504.16417 2025-11-18 eess.SY cs.SY 50%

Anytime Safe Reinforcement Learning

Pol Mestres, Arnau Marzabal, Jorge Cortés

专题命中模仿学习与强化学习：navigation(abstract)

2501.16436 2025-11-04 quant-ph 50%

Taming quantum systems: A tutorial for using shortcuts-to-adiabaticity, quantum optimal control, and reinforcement learning

Callum W. Duncan, Pablo M. Poggi, Marin Bukov, Nikolaj Thomas Zinner, Steve Campbell

专题命中模仿学习与强化学习：manipulation(abstract)

Comments 73 pages, 15 figures. Data associated with this manuscript version are openly available on Zenodo, https://doi.org/10.5281/zenodo.17169846 ; Jupyter notebooks are available on GitHub, https://github.com/nqd-lab/quctrl-tutorial

Journal ref PRX Quantum 6, 040201 (2025)

2410.20907 2025-10-30 eess.SY cs.SY 50%

Combining Deep Reinforcement Learning with a Jerk-Bounded Trajectory Generator for Kinematically Constrained Motion Planning

Seyed Adel Alizadeh Kolagar, Mehdi Heydari Shahna, Jouni Mattila

专题命中模仿学习与强化学习：robotic(abstract)

Comments This paper has been submitted to the IEEE for potential publication

2510.01492 2025-10-03 eess.SY cs.SY 50%

Off-Policy Reinforcement Learning with Anytime Safety Guarantees via Robust Safe Gradient Flow

Pol Mestres, Arnau Marzabal, Jorge Cortés

专题命中模仿学习与强化学习：navigation(abstract)

2509.23425 2025-09-30 cs.MA 50%

Situational Awareness for Safe and Robust Multi-Agent Interactions Under Uncertainty

Benjamin Alcorn, Eman Hammad

专题命中模仿学习与强化学习：robotics(abstract)

2509.03479 2025-09-04 cs.CL 50%

Design and Optimization of Reinforcement Learning-Based Agents in Text-Based Games

Haonan Wang, Mingjia Zhao, Junfeng Sun, Wei Liu

专题命中模仿学习与强化学习：world model(abstract)

Comments 6 papges

Journal ref Copyright (c) 2025 International Journal of Computer Science and Information Technology International Journal of Computer Science and Information Technology International Journal of Computer Science and Information Technology

2508.17185 2025-08-26 math.OC cs.SY eess.SY 50%

Linear Dynamics meets Linear MDPs: Closed-Form Optimal Policies via Reinforcement Learning

Abed AlRahman Al Makdah, Oliver Kosut, Lalitha Sankar, Shaofeng Zou

专题命中模仿学习与强化学习：robotics(abstract)

2506.05236 2025-08-08 cs.MA 50%

Towards Language-Augmented Multi-Agent Deep Reinforcement Learning

Maxime Toquebiau, Jae-Yun Jun, Faïz Benamar, Nicolas Bredeche

专题命中模仿学习与强化学习：embodied agent(abstract)

Comments Accespted at the European Conference on Artificial Intelligence 2025

2508.00645 2025-08-04 physics.flu-dyn physics.comp-ph 50%

SmartFlow: A CFD-solver-agnostic deep reinforcement learning framework for computational fluid dynamics on HPC platforms

Maochao Xiao, Yuning Wang, Felix Rodach, Bernat Font, Marius Kurz, Pol Suárez, Di Zhou, Francisco Alcántara-Ávila, Ting Zhu, Junle Liu, Ricard Montalà, Jiawei Chen, Jean Rabault, Oriol Lehmkuhl, Andrea Beck, Johan Larsson, Ricardo Vinuesa, Sergio Pirozzoli

专题命中模仿学习与强化学习：navigation(abstract)

2507.23080 2025-08-01 cs.MA 50%

Causal-Inspired Multi-Agent Decision-Making via Graph Reinforcement Learning

Jing Wang, Yan Jin, Fei Ding, Chongfeng Wei

专题命中模仿学习与强化学习：navigation(abstract)

2412.04053 2025-07-10 quant-ph 50%

Enhanced Qubit Readout via Reinforcement Learning

Aniket Chatterjee, Jonathan Schwinger, Yvonne Y. Gao

专题命中模仿学习与强化学习：manipulation(abstract)

Comments 11 pages, 4 figures

Journal ref Phys. Rev. Applied 23, 054057 (2025)

2505.13543 2025-07-09 cs.MA cs.CY 50%

Origin-Destination Pattern Effects on Large-Scale Mixed Traffic Control via Multi-Agent Reinforcement Learning

Muyang Fan, Songyang Liu, Shuai Li, Weizi Li

专题命中模仿学习与强化学习：robotic(abstract)

Comments Accepted to IEEE International Conference on Intelligent Transportation Systems (ITSC), 2025

2507.04998 2025-07-08 q-bio.NC 50%

Linking Homeostasis to Reinforcement Learning: Internal State Control of Motivated Behavior

Naoto Yoshida, Henning Sprekeler, Boris Gutkin

专题命中模仿学习与强化学习：robotic(abstract)

2507.04160 2025-07-08 cs.HC 50%

HyperSumm-RL: A Dialogue Summarization Framework for Modeling Leadership Perception in Social Robots

Subasish Das

专题命中模仿学习与强化学习：navigation(abstract)

Comments 6 pages with references

2501.03948 2025-07-08 cond-mat.stat-mech cond-mat.soft 50%

Kinetic theory of decentralized learning for smart active matter

Gerhard Jung, Misaki Ozawa, Eric Bertin

专题命中模仿学习与强化学习：robotics(abstract)

Comments Phys. Rev. Lett. 134, 248302 (Editors' Suggestion)

2506.22112 2025-07-01 cs.IR 50%

Reward Balancing Revisited: Enhancing Offline Reinforcement Learning for Recommender Systems

Wenzheng Shu, Yanxiang Zeng, Yongxiang Tang, Teng Sha, Ning Luo, Yanhua Cheng, Xialong Liu, Fan Zhou, Peng Jiang

专题命中模仿学习与强化学习：world model(abstract)

Comments Accepted in Companion Proceedings of the ACM Web Conference 2025

2506.12497 2025-06-19 eess.SY cs.SY 50%

Wasserstein-Barycenter Consensus for Cooperative Multi-Agent Reinforcement Learning

Ali Baheri

专题命中模仿学习与强化学习：navigation(abstract)

2506.01710 2025-06-03 cs.CL 50%

Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning

Fangyu Lei, Jinxiang Meng, Yiming Huang, Tinghong Chen, Yun Zhang, Shizhu He, Jun Zhao, Kang Liu

机构 * Institute of Automation, CAS（中国科学院自动化研究所）； University of Chinese Academy of Sciences（中国科学院大学）

专题命中模仿学习与强化学习：manipulation(abstract)

Comments Work in progress

1. 模仿学习与强化学习 4116 篇

Towards Dynamic Quadrupedal Gaits: A Symmetry-Guided RL Hierarchy Enables Free Gait Transitions at Varying Speeds

A Cognitive Framework for Autonomous Agents: Toward Human-Inspired Design

Dynamic Tactile Sensing System and Soft Actor Critic Reinforcement Learning for Inclusion Characterization

UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning

NeuRehab: A Reinforcement Learning and Spiking Neural Network-Based Rehab Automation Framework

On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models

Analyzing Collision Rates in Large-Scale Mixed Traffic Control via Multi-Agent Reinforcement Learning

Comparative Analysis of Autonomous and Systematic Control Strategies for Hole-Doped Hubbard Clusters: Reinforcement Learning versus Physics-Guided Design

Optimality and Suboptimality of MPPI Control in Stochastic and Deterministic Settings

MARL-CC: A Mathematical Framework forMulti-Agent Reinforcement Learning in ConnectedAutonomous Vehicles: Addressing Nonlinearity,Partial Observability, and Credit Assignment forOptimal Control

LLM4Laser: Large Language Models Automate the Design of Lasers

Law-Strength Frontiers and a No-Free-Lunch Result for Law-Seeking Reinforcement Learning on Volatility Law Manifolds

Anytime Safe Reinforcement Learning

Taming quantum systems: A tutorial for using shortcuts-to-adiabaticity, quantum optimal control, and reinforcement learning

Combining Deep Reinforcement Learning with a Jerk-Bounded Trajectory Generator for Kinematically Constrained Motion Planning

Off-Policy Reinforcement Learning with Anytime Safety Guarantees via Robust Safe Gradient Flow

Situational Awareness for Safe and Robust Multi-Agent Interactions Under Uncertainty

Design and Optimization of Reinforcement Learning-Based Agents in Text-Based Games

Linear Dynamics meets Linear MDPs: Closed-Form Optimal Policies via Reinforcement Learning

Towards Language-Augmented Multi-Agent Deep Reinforcement Learning

SmartFlow: A CFD-solver-agnostic deep reinforcement learning framework for computational fluid dynamics on HPC platforms

Causal-Inspired Multi-Agent Decision-Making via Graph Reinforcement Learning

Enhanced Qubit Readout via Reinforcement Learning

Origin-Destination Pattern Effects on Large-Scale Mixed Traffic Control via Multi-Agent Reinforcement Learning

Linking Homeostasis to Reinforcement Learning: Internal State Control of Motivated Behavior

HyperSumm-RL: A Dialogue Summarization Framework for Modeling Leadership Perception in Social Robots

Kinetic theory of decentralized learning for smart active matter

Reward Balancing Revisited: Enhancing Offline Reinforcement Learning for Recommender Systems

Wasserstein-Barycenter Consensus for Cooperative Multi-Agent Reinforcement Learning

Reasoning-Table: Exploring Reinforcement Learning for Table Reasoning