机器人 / 具身智能 - arXivDaily 专题

2412.16145 2024-12-30 cs.LG cs.AI cs.CL 62%

Offline Reinforcement Learning for LLM Multi-Step Reasoning

Huaijie Wang, Shibo Hao, Hanze Dong, Shenao Zhang, Yilin Bao, Ziran Yang, Yi Wu

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

2412.15525 2024-12-23 cs.LG cs.AI 62%

Generalized Back-Stepping Experience Replay in Sparse-Reward Environments

Guwen Lyu, Masahiro Sato

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

2309.07675 2024-12-20 cs.LG cs.AI 62%

Goal Space Abstraction in Hierarchical Reinforcement Learning via Set-Based Reachability Analysis

Mehdi Zadem, Sergio Mover, Sao Mai Nguyen

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

2412.13492 2024-12-19 cs.RO cs.LG 62%

Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution

Changxin Huang, Yanbin Chang, Junfan Lin, Junyang Liang, Runhao Zeng, Jianqiang Li

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

Comments 14 pages, 5 figures, published to AAAI2025

2412.12953 2024-12-18 cs.LG cs.RO 62%

Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning

Moritz Reuss, Jyothish Pari, Pulkit Agrawal, Rudolf Lioutikov

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

2406.06460 2024-12-16 cs.RO cs.AI 62%

Towards Real-World Efficiency: Domain Randomization in Reinforcement Learning for Pre-Capture of Free-Floating Moving Targets by Autonomous Robots

Bahador Beigomi, Zheng H. Zhu

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

Comments This is a preprint for the work submitted to the ICRA 2024 conference

2407.16677 2024-12-13 cs.RO cs.LG 62%

From Imitation to Refinement -- Residual RL for Precise Assembly

Lars Ankile, Anthony Simeonov, Idan Shenfeld, Marcel Torne, Pulkit Agrawal

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

Comments Project website: https://residual-assembly.github.io

2412.06685 2024-12-10 cs.LG cs.AI 62%

Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone

Max Sobol Mark, Tian Gao, Georgia Gabriela Sampaio, Mohan Kumar Srirama, Archit Sharma, Chelsea Finn, Aviral Kumar

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

2407.08464 2024-12-10 cs.LG cs.AI 62%

TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations

Junik Bae, Kwanyoung Park, Youngwoon Lee

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

Comments CoRL 2024

2412.05766 2024-12-10 cs.LG cs.AI 62%

Policy-shaped prediction: avoiding distractions in model-based reinforcement learning

Miles Hutson, Isaac Kauvar, Nick Haber

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

Comments Accepted at NeurIPS 2024

2202.02404 2024-12-05 cs.AI cs.LO cs.RO 62%

Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives

Anand Balakrishnan, Stefan Jakšić, Edgar A. Aguilar, Dejan Ničković, Jyotirmoy V. Deshmukh

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

2407.15007 2024-12-03 cs.LG cs.AI math.ST stat.ML stat.TH 62%

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning

Dylan J. Foster, Adam Block, Dipendra Misra

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

Comments NeurIPS 2024

2412.00086 2024-12-03 cs.RO cs.LG 62%

Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning

Neel Jawale, Byron Boots, Balakumar Sundaralingam, Mohak Bhardwaj

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

Comments 11 pages

2412.00084 2024-12-03 cs.LG cs.RO 62%

Unpacking the Individual Components of Diffusion Policy

Xiu Yuan

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

2411.17764 2024-11-28 cs.RO cs.AI 62%

PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement

Tewodros Ayalew, Xiao Zhang, Kevin Yuanbo Wu, Tianchong Jiang, Michael Maire, Matthew R. Walter

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

Comments 15 pages,13 figures

2409.07932 2024-11-27 cs.LG cs.AI cs.MA cs.SI 62%

Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies

Alexei Pisacane, Victor-Alexandru Darvariu, Mirco Musolesi

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

Journal ref Proceedings of the Third Learning on Graphs Conference (LoG 2024), PMLR 269

2411.17137 2024-11-27 cs.RO cs.AI 62%

Self-reconfiguration Strategies for Space-distributed Spacecraft

Tianle Liu, Zhixiang Wang, Yongwei Zhang, Ziwei Wang, Zihao Liu, Yizhai Zhang, Panfeng Huang

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

2411.03555 2024-11-07 cs.CV cs.RO 62%

Object and Contact Point Tracking in Demonstrations Using 3D Gaussian Splatting

Michael Büttner, Jonathan Francis, Helge Rhodin, Andrew Melnik

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

Comments CoRL 2024, Workshop on Lifelong Learning for Home Robots, Munich, Germany

2411.02345 2024-11-05 cs.RO cs.AI physics.med-ph q-bio.OT 62%

Simulation of Nanorobots with Artificial Intelligence and Reinforcement Learning for Advanced Cancer Cell Detection and Tracking

Shahab Kavousinejad

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

Comments The source code for this simulation is available on GitHub: https://github.com/SHAHAB-K93/cancer-and-smart-nanorobot

2410.23535 2024-11-01 cs.CL cs.AI cs.RO 62%

Simulating User Agents for Embodied Conversational-AI

Daniel Philipov, Vardhan Dongre, Gokhan Tur, Dilek Hakkani-Tür

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

Comments 8 pages, 5 figures, 4 tables

Journal ref NeurIPS 2024 Workshop on Open-World Agents

2410.14916 2024-10-30 cs.MA cs.AI cs.RO 62%

Cooperation and Fairness in Multi-Agent Reinforcement Learning

Jasmine Jerry Aloor, Siddharth Nayak, Sydney Dolan, Hamsa Balakrishnan

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

Comments Manuscript accepted in ACM Journal on Autonomous Transportation Systems

2401.00330 2024-10-28 cs.LG cs.AI 62%

Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions

Yinglun Xu, Tarun Suresh, Rohan Gumaste, David Zhu, Ruirui Li, Zhengyang Wang, Haoming Jiang, Xianfeng Tang, Qingyu Yin, Monica Xiao Cheng, Qi Zeng, Chao Zhang, Gagandeep Singh

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

2309.03157 2024-10-28 cs.RO cs.LG 62%

Learning to Recharge: UAV Coverage Path Planning through Deep Reinforcement Learning

Mirco Theile, Harald Bayerlein, Marco Caccamo, Alberto L. Sangiovanni-Vincentelli

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

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

2203.04927 2024-10-28 cs.LG cs.AI 62%

Investigation of Factorized Optical Flows as Mid-Level Representations

Hsuan-Kung Yang, Tsu-Ching Hsiao, Ting-Hsuan Liao, Hsu-Shen Liu, Li-Yuan Tsao, Tzu-Wen Wang, Shan-Ya Yang, Yu-Wen Chen, Huang-Ru Liao, Chun-Yi Lee

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

Comments Ting-Hsuan Liao, Hsu-Shen Liu, Li-Yuan Tsao, Tzu-Wen Wang, and Shan-Ya Yang contributed equally to this work, names listed in alphabetical order; This work has been submitted to the IEEE for possible publication

Journal ref 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

1705.08439 2024-10-25 cs.AI cs.LG 62%

Thinking Fast and Slow with Deep Learning and Tree Search

Thomas Anthony, Zheng Tian, David Barber

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

Comments v1 to v2: - Add a value function in MCTS - Some MCTS hyper-parameters changed - Repetition of experiments: improved accuracy and errors shown. (note the reduction in effect size for the tpt/cat experiment) - Results from a longer training run, including changes in expert strength in training - Comparison to MoHex. v3: clarify independence of ExIt and AG0. v4: see appendix E

2410.17551 2024-10-24 cs.LG cs.RO 62%

Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensors

Bang You, Huaping Liu

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

Comments 31 pages

Journal ref Neural Networks, 176(2024)

2410.17186 2024-10-23 cs.RO cs.AI 62%

DyPNIPP: Predicting Environment Dynamics for RL-based Robust Informative Path Planning

Srujan Deolasee, Siva Kailas, Wenhao Luo, Katia Sycara, Woojun Kim

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

Comments 8 pages, 4 figures, submitted to IEEE RA-L

2410.15600 2024-10-22 cs.AI cs.GT cs.RO 62%

Patrol Security Game: Defending Against Adversary with Freedom in Attack Timing, Location, and Duration

Hao-Tsung Yang, Ting-Kai Weng, Ting-Yu Chang, Kin Sum Liu, Shan Lin, Jie Gao, Shih-Yu Tsai

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

Comments Under review of TCPS

2403.10940 2024-10-22 cs.RO cs.LG 62%

ViSaRL: Visual Reinforcement Learning Guided by Human Saliency

Anthony Liang, Jesse Thomason, Erdem Bıyık

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

Journal ref IEEE/RSJ International Conference on Intelligent Robots and Systems 2024

2306.09509 2024-10-22 cs.AI cs.RO 62%

Granger Causal Interaction Skill Chains

Caleb Chuck, Kevin Black, Aditya Arjun, Yuke Zhu, Scott Niekum

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

Comments Accepted TMLR 2024

1. 模仿学习与强化学习 4115 篇

Offline Reinforcement Learning for LLM Multi-Step Reasoning

Generalized Back-Stepping Experience Replay in Sparse-Reward Environments

Goal Space Abstraction in Hierarchical Reinforcement Learning via Set-Based Reachability Analysis

Efficient Language-instructed Skill Acquisition via Reward-Policy Co-Evolution

Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning

Towards Real-World Efficiency: Domain Randomization in Reinforcement Learning for Pre-Capture of Free-Floating Moving Targets by Autonomous Robots

From Imitation to Refinement -- Residual RL for Precise Assembly

Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone

TLDR: Unsupervised Goal-Conditioned RL via Temporal Distance-Aware Representations

Policy-shaped prediction: avoiding distractions in model-based reinforcement learning

Model-Free Reinforcement Learning for Symbolic Automata-encoded Objectives

Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning

Dynamic Non-Prehensile Object Transport via Model-Predictive Reinforcement Learning

Unpacking the Individual Components of Diffusion Policy

PROGRESSOR: A Perceptually Guided Reward Estimator with Self-Supervised Online Refinement

Reinforcement Learning Discovers Efficient Decentralized Graph Path Search Strategies

Self-reconfiguration Strategies for Space-distributed Spacecraft

Object and Contact Point Tracking in Demonstrations Using 3D Gaussian Splatting

Simulation of Nanorobots with Artificial Intelligence and Reinforcement Learning for Advanced Cancer Cell Detection and Tracking

Simulating User Agents for Embodied Conversational-AI

Cooperation and Fairness in Multi-Agent Reinforcement Learning

Two-Step Offline Preference-Based Reinforcement Learning with Constrained Actions

Learning to Recharge: UAV Coverage Path Planning through Deep Reinforcement Learning

Investigation of Factorized Optical Flows as Mid-Level Representations

Thinking Fast and Slow with Deep Learning and Tree Search

Multimodal Information Bottleneck for Deep Reinforcement Learning with Multiple Sensors

DyPNIPP: Predicting Environment Dynamics for RL-based Robust Informative Path Planning

Patrol Security Game: Defending Against Adversary with Freedom in Attack Timing, Location, and Duration

ViSaRL: Visual Reinforcement Learning Guided by Human Saliency

Granger Causal Interaction Skill Chains