机器人 / 具身智能 - arXivDaily 专题

2211.11602 2022-11-22 cs.LG cs.HC cs.MA 57%

Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback

Josh Abramson, Arun Ahuja, Federico Carnevale, Petko Georgiev, Alex Goldin, Alden Hung, Jessica Landon, Jirka Lhotka, Timothy Lillicrap, Alistair Muldal, George Powell, Adam Santoro, Guy Scully, Sanjana Srivastava, Tamara von Glehn, Greg Wayne, Nathaniel Wong, Chen Yan, Rui Zhu

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

2211.11391 2022-11-22 cs.RO cs.SY eess.SY 57%

Reinforcement Learning-Enhanced Control Barrier Functions for Robot Manipulators

Stephen McIlvanna, Nhat Nguyen Minh, Yuzhu Sun, Mien Van, Wasif Naeem

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

2206.07922 2022-11-09 cs.LG 57%

Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications

Sai Munikoti, Deepesh Agarwal, Laya Das, Mahantesh Halappanavar, Balasubramaniam Natarajan

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

Comments 20 pages, 3 figures, 2 tables

2211.00942 2022-11-03 cs.LG 57%

Model-based Reinforcement Learning with a Hamiltonian Canonical ODE Network

Yao Feng, Yuhong Jiang, Hang Su, Dong Yan, Jun Zhu

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

2211.00688 2022-11-03 cs.AI cs.CL 57%

Learning to Solve Voxel Building Embodied Tasks from Pixels and Natural Language Instructions

Alexey Skrynnik, Zoya Volovikova, Marc-Alexandre Côté, Anton Voronov, Artem Zholus, Negar Arabzadeh, Shrestha Mohanty, Milagro Teruel, Ahmed Awadallah, Aleksandr Panov, Mikhail Burtsev, Julia Kiseleva

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

Comments 6 pages, 3 figures

2210.01808 2022-11-02 cs.LG stat.ML 57%

Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees

Siliang Zeng, Chenliang Li, Alfredo Garcia, Mingyi Hong

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

Comments Two different versions (arXiv:2210.01808 and arXiv:2210.01282) of the same paper have been submitted to arxiv. To avoid to the overlap between two versions, we withdraw this version. For this paper, readers could refer to arXiv:2210.01282

2205.14953 2022-10-31 cs.MA cs.LG 57%

Multi-Agent Reinforcement Learning is a Sequence Modeling Problem

Muning Wen, Jakub Grudzien Kuba, Runji Lin, Weinan Zhang, Ying Wen, Jun Wang, Yaodong Yang

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

2210.15199 2022-10-28 cs.RO 57%

Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection

Catherine R. Glossop, Jacopo Panerati, Amrit Krishnan, Zhaocong Yuan, Angela P. Schoellig

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

Comments 18 pages, 15 figures

2203.07709 2022-10-28 cs.RO 57%

Adaptive Environment Modeling Based Reinforcement Learning for Collision Avoidance in Complex Scenes

Shuaijun Wang, Rui Gao, Ruihua Han, Shengduo Chen, Chengyang Li, Qi Hao

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

Comments accepted by IROS2022

2210.12927 2022-10-25 cs.RO 57%

The Design and Realization of Multi-agent Obstacle Avoidance based on Reinforcement Learning

Enyu Zhao, Chanjuan Liu, Houfu Su, Yang Liu

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

2210.11126 2022-10-21 cs.RO 57%

Co-Training an Observer and an Evading Target

André Brandenburger, Folker Hoffmann, Alexander Charlish

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

Comments Accepted for IEEE 24th International Conference on Information Fusion (FUSION 2021)

2210.07636 2022-10-17 cs.LG cs.MA 57%

Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning

Jifeng Hu, Yanchao Sun, Hechang Chen, Sili Huang, haiyin piao, Yi Chang, Lichao Sun

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

2210.06526 2022-10-14 cond-mat.dis-nn cs.LG 57%

Microscopy is All You Need

Sergei V. Kalinin, Rama Vasudevan, Yongtao Liu, Ayana Ghosh, Kevin Roccapriore, Maxim Ziatdinov

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

2205.05138 2022-10-13 cs.LG 57%

Efficient Risk-Averse Reinforcement Learning

Ido Greenberg, Yinlam Chow, Mohammad Ghavamzadeh, Shie Mannor

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

Comments Accepted to NeurIPS 2022

2210.05650 2022-10-12 cs.LG 57%

Regret Bounds for Risk-Sensitive Reinforcement Learning

O. Bastani, Y. J. Ma, E. Shen, W. Xu

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

2210.04209 2022-10-11 cs.LG 57%

Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning

Yao Mu, Yuzheng Zhuang, Fei Ni, Bin Wang, Jianyu Chen, Jianye Hao, Ping Luo

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

Comments NeurIPS 2022

2209.12295 2022-09-27 cs.LG 57%

Gradient Optimization for Single-State RMDPs

Keith Badger

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

Comments 16 pages, 6 figures

2111.11156 2022-09-27 cs.RO 57%

Improved Reinforcement Learning Pushing Policies via Heuristic Rules

Marios Kiatos, Iason Sarantopoulos, Sotiris Malassiotis, Zoe Doulgeri

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

2209.11787 2022-09-27 cs.RO 57%

Synthesize Efficient Safety Certificates for Learning-Based Safe Control using Magnitude Regularization

Haotian Zheng, Haitong Ma, Sifa Zheng, Shengbo Eben Li, Jianqiang Wang

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

Comments 8 pages, 6 figures

2111.12600 2022-09-26 cs.LG 57%

Learning State Representations via Retracing in Reinforcement Learning

Changmin Yu, Dong Li, Jianye Hao, Jun Wang, Neil Burgess

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

2106.07854 2022-09-23 cs.AI 57%

Population-coding and Dynamic-neurons improved Spiking Actor Network for Reinforcement Learning

Duzhen Zhang, Tielin Zhang, Shuncheng Jia, Xiang Cheng, Bo Xu

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

2209.07096 2022-09-16 cs.AI 57%

Multi-Objective Policy Gradients with Topological Constraints

Kyle Hollins Wray, Stas Tiomkin, Mykel J. Kochenderfer, Pieter Abbeel

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

2209.06622 2022-09-15 cs.RO 57%

Distributed Multi-Robot Obstacle Avoidance via Logarithmic Map-based Deep Reinforcement Learning

Jiafeng Ma, Guangda chen, Yingfeng Chen, Yujing Hu, Changjie Fan, Jianming Zhang

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

2208.13663 2022-08-30 cs.LG cs.CR stat.ML 57%

Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning

Anshuka Rangi, Haifeng Xu, Long Tran-Thanh, Massimo Franceschetti

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

Comments Accepted at International Joint Conferences on Artificial Intelligence (IJCAI) 2022

2108.08628 2022-08-30 eess.SP cs.LG 57%

A Reinforcement Learning Approach for GNSS Spoofing Attack Detection of Autonomous Vehicles

Sagar Dasgupta, Tonmoy Ghosh, Mizanur Rahman

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

2111.00213 2022-08-23 cs.LG 57%

Adjacency constraint for efficient hierarchical reinforcement learning

Tianren Zhang, Shangqi Guo, Tian Tan, Xiaolin Hu, Feng Chen

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

Comments Accepted by IEEE Transactions on Pattern Analysis and Machine Intelligence. DOI: 10.1109/TPAMI.2022.3192418. arXiv admin note: substantial text overlap with arXiv:2006.11485

2208.03663 2022-08-09 cs.MA cs.LG 57%

Maximum Correntropy Value Decomposition for Multi-agent Deep Reinforcemen Learning

Kai Liu, Tianxian Zhang, Lingjiang Kong

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

Comments under review

2207.13813 2022-07-29 cs.LG 57%

Structural Similarity for Improved Transfer in Reinforcement Learning

C. Chace Ashcraft, Benjamin Stoler, Chigozie Ewulum, Susama Agarwala

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

2205.03130 2022-07-27 cs.LG 57%

SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning

Bian Xihan, Oscar Mendez, Simon Hadfield

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

Comments Submitted to IROS 2022, under review

2012.11641 2022-07-19 cs.RO 57%

Multi-Agent Reinforcement Learning for Dynamic Ocean Monitoring by a Swarm of Buoys

Maryam Kouzehgar, Malika Meghjani, Roland Bouffanais

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

Comments Accepted for Publication at IEEE/MTS OCEANS 2020

Journal ref in Proceedings of Global Oceans 2020: Singapore-US Gulf Coast (pp. 1-8). IEEE

1. 模仿学习与强化学习 4134 篇

Improving Multimodal Interactive Agents with Reinforcement Learning from Human Feedback

Reinforcement Learning-Enhanced Control Barrier Functions for Robot Manipulators

Challenges and Opportunities in Deep Reinforcement Learning with Graph Neural Networks: A Comprehensive review of Algorithms and Applications

Model-based Reinforcement Learning with a Hamiltonian Canonical ODE Network

Learning to Solve Voxel Building Embodied Tasks from Pixels and Natural Language Instructions

Maximum-Likelihood Inverse Reinforcement Learning with Finite-Time Guarantees

Multi-Agent Reinforcement Learning is a Sequence Modeling Problem

Characterising the Robustness of Reinforcement Learning for Continuous Control using Disturbance Injection

Adaptive Environment Modeling Based Reinforcement Learning for Collision Avoidance in Complex Scenes

The Design and Realization of Multi-agent Obstacle Avoidance based on Reinforcement Learning

Co-Training an Observer and an Evading Target

Distributional Reward Estimation for Effective Multi-Agent Deep Reinforcement Learning

Microscopy is All You Need

Efficient Risk-Averse Reinforcement Learning

Regret Bounds for Risk-Sensitive Reinforcement Learning

Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning

Gradient Optimization for Single-State RMDPs

Improved Reinforcement Learning Pushing Policies via Heuristic Rules

Synthesize Efficient Safety Certificates for Learning-Based Safe Control using Magnitude Regularization

Learning State Representations via Retracing in Reinforcement Learning

Population-coding and Dynamic-neurons improved Spiking Actor Network for Reinforcement Learning

Multi-Objective Policy Gradients with Topological Constraints

Distributed Multi-Robot Obstacle Avoidance via Logarithmic Map-based Deep Reinforcement Learning

Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning

A Reinforcement Learning Approach for GNSS Spoofing Attack Detection of Autonomous Vehicles

Adjacency constraint for efficient hierarchical reinforcement learning

Maximum Correntropy Value Decomposition for Multi-agent Deep Reinforcemen Learning

Structural Similarity for Improved Transfer in Reinforcement Learning

SKILL-IL: Disentangling Skill and Knowledge in Multitask Imitation Learning

Multi-Agent Reinforcement Learning for Dynamic Ocean Monitoring by a Swarm of Buoys