AI Agent - arXivDaily 专题

2203.08553 2023-02-23 cs.MA cs.AI 88%

PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration

Pengyi Li, Hongyao Tang, Tianpei Yang, Xiaotian Hao, Tong Sang, Yan Zheng, Jianye Hao, Matthew E. Taylor, Wenyuan Tao, Zhen Wang, Fazl Barez

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

Comments The paper has been accepted by The Thirty-ninth International Conference on Machine Learning (ICML 2022) and the Cooperative AI Workshop at 35th Conference on Neural Information Processing Systems (NeurIPS 2021)

2302.10825 2023-02-22 cs.AI 88%

Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning

Jiong Li, Pratik Gajane

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

2112.11937 2023-02-22 cs.AI 88%

Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies

Aizaz Sharif, Dusica Marijan

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

2302.09605 2023-02-21 cs.LG cs.MA 88%

Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning

Cong Guan, Feng Chen, Lei Yuan, Zongzhang Zhang, Yang Yu

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

2302.09531 2023-02-21 cs.LG cs.MA 88%

AIIR-MIX: Multi-Agent Reinforcement Learning Meets Attention Individual Intrinsic Reward Mixing Network

Wei Li, Weiyan Liu, Shitong Shao, Shiyi Huang

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

2302.06872 2023-02-15 cs.RO cs.AI cs.MA 88%

Adaptive Value Decomposition with Greedy Marginal Contribution Computation for Cooperative Multi-Agent Reinforcement Learning

Shanqi Liu, Yujing Hu, Runze Wu, Dong Xing, Yu Xiong, Changjie Fan, Kun Kuang, Yong Liu

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

Comments This paper is accepted by aamas 2023

2302.06569 2023-02-14 cs.LG cs.MA 88%

Inferring Player Location in Sports Matches: Multi-Agent Spatial Imputation from Limited Observations

Gregory Everett, Ryan J. Beal, Tim Matthews, Joseph Early, Timothy J. Norman, Sarvapali D. Ramchurn

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

Comments 11 Pages (8 main, 1 references, 2 appendix), 8 figures (7 main, 1 appendix). Accepted at AAMAS 2023 Main Track

2302.05528 2023-02-14 cs.AI cs.MA cs.RO 88%

Learning cooperative behaviours in adversarial multi-agent systems

Ni Wang, Gautham P. Das, Alan G. Millard

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

Comments 23rd Annual Conference, Towards Autonomous Robotic Systems 2022

Journal ref Lecture Notes in Computer Science(), vol 13546. Springer, Cham. 2022

2302.05055 2023-02-13 cs.MA cs.LG 88%

Low Entropy Communication in Multi-Agent Reinforcement Learning

Lebin Yu, Yunbo Qiu, Qiexiang Wang, Xudong Zhang, Jian Wang

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

Comments Accpeted by ICC 2023

2209.13565 2023-02-13 math.OC cs.LG 88%

Neural parameter calibration for large-scale multi-agent models

Thomas Gaskin, Grigorios A. Pavliotis, Mark Girolami

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

Journal ref PNAS 2023

2302.04094 2023-02-09 cs.RO cs.AI cs.MA 88%

Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation

Xinyi Yang, Shiyu Huang, Yiwen Sun, Yuxiang Yang, Chao Yu, Wei-Wei Tu, Huazhong Yang, Yu Wang

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

Comments This paper is accepted by aamas 2023

2209.08244 2023-02-08 cs.LG cs.MA 88%

MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning

Kefan Su, Siyuan Zhou, Jiechuan Jiang, Chuang Gan, Xiangjun Wang, Zongqing Lu

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

Comments 18 pages

2203.00076 2023-01-30 cs.LG cs.MA stat.ML 88%

Robust Multi-Agent Bandits Over Undirected Graphs

Daniel Vial, Sanjay Shakkottai, R. Srikant

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

Journal ref Proceedings of the ACM on Measurement and Analysis of Computing Systems, December 2022

2202.12927 2023-01-26 math.AP cs.LG cs.NA math.NA math.OC 88%

A blob method for inhomogeneous diffusion with applications to multi-agent control and sampling

Katy Craig, Karthik Elamvazhuthi, Matt Haberland, Olga Turanova

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

Comments 56 pages, 8 figures

2301.09689 2023-01-25 cs.MA cs.LG 88%

Graph Neural Networks for Decentralized Multi-Agent Perimeter Defense

Elijah S. Lee, Lifeng Zhou, Alejandro Ribeiro, Vijay Kumar

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

Comments 20 pages, 10 figures. Published in Frontiers in Control Engineering 2023. arXiv admin note: substantial text overlap with arXiv:2211.01757

2301.08864 2023-01-24 cs.MA cs.AI 88%

Decentralized Multi-agent Filtering

Dom Huh, Prasant Mohapatra

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

2301.08687 2023-01-23 cs.AI 88%

Counterexample Guided Abstraction Refinement with Non-Refined Abstractions for Multi-Agent Path Finding

Pavel Surynek

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

2111.01946 2023-01-18 cs.LG 88%

Robust Dynamic Bus Control: A Distributional Multi-agent Reinforcement Learning Approach

Jiawei Wang, Lijun Sun

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

Journal ref IEEE Transactions on Intelligent Transportation Systems (2022)

2206.06758 2023-01-16 cs.MA cs.DM cs.LG 88%

Universally Expressive Communication in Multi-Agent Reinforcement Learning

Matthew Morris, Thomas D. Barrett, Arnu Pretorius

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

Comments Published in NeurIPS 2022

2005.14220 2023-01-05 cs.IT cs.LG cs.MA cs.SY eess.SY math.IT 88%

Task-Oriented Data Compression for Multi-Agent Communications Over Bit-Budgeted Channels

Arsham Mostaani, Thang X. Vu, Symeon Chatzinotas, Björn Ottersten

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

Comments 19 pages, 11 figures

Journal ref IEEE Open Journal of the Communications Society, vol. 3, pp. 1867-1886, 2022

2112.10374 2023-01-02 cs.AI cs.MA 88%

CGIBNet: Bandwidth-constrained Communication with Graph Information Bottleneck in Multi-Agent Reinforcement Learning

Qi Tian, Kun Kuang, Baoxiang Wang, Furui Liu, Fei Wu

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

2212.13379 2022-12-29 cs.MA cs.AI 88%

Learning Individual Policies in Large Multi-agent Systems through Local Variance Minimization

Tanvi Verma, Pradeep Varakantham

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

Comments arXiv admin note: substantial text overlap with arXiv:2003.07088

2212.11746 2022-12-23 cs.LG cs.MA 88%

Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning

Ronghui Mu, Wenjie Ruan, Leandro Soriano Marcolino, Gaojie Jin, Qiang Ni

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

Comments This paper will appear in AAAI2023

2212.10064 2022-12-21 cs.RO cs.LG cs.MA cs.SY eess.SY math.OC 88%

AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning

Aowabin Rahman, Arnab Bhattacharya, Thiagarajan Ramachandran, Sayak Mukherjee, Himanshu Sharma, Ted Fujimoto, Samrat Chatterjee

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

2212.09926 2022-12-21 cs.AI cs.MA physics.optics quant-ph 88%

Bandit approach to conflict-free multi-agent Q-learning in view of photonic implementation

Hiroaki Shinkawa, Nicolas Chauvet, André Röhm, Takatomo Mihana, Ryoichi Horisaki, Guillaume Bachelier, Makoto Naruse

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

Comments 19 pages, 8 figures, 1 table

2212.08710 2022-12-20 cs.MA cs.LG cs.RO 88%

JFP: Joint Future Prediction with Interactive Multi-Agent Modeling for Autonomous Driving

Wenjie Luo, Cheolho Park, Andre Cornman, Benjamin Sapp, Dragomir Anguelov

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

2212.07967 2022-12-16 eess.SY cs.LG cs.MA cs.SY 88%

Distributed-Training-and-Execution Multi-Agent Reinforcement Learning for Power Control in HetNet

Kaidi Xu, Nguyen Van Huynh, Geoffrey Ye Li

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.LG

2212.06940 2022-12-15 cs.AI cs.MA 88%

Heuristically Guided Compilation for Multi-Agent Path Finding

Pavel Surynek

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

Comments arXiv admin note: substantial text overlap with arXiv:2103.04496

2206.13441 2022-12-13 cs.AI cs.SY eess.SY 88%

EMVLight: a Multi-agent Reinforcement Learning Framework for an Emergency Vehicle Decentralized Routing and Traffic Signal Control System

Haoran Su, Yaofeng D. Zhong, Joseph Y. J. Chow, Biswadip Dey, Li Jin

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

Comments 19 figures, 10 tables. Manuscript extended on previous work arXiv:2109.05429, arXiv:2111.00278

Journal ref Transportation Research Part C: Emerging Technologies Volume 146, January 2023, 103955

2212.03461 2022-12-08 cs.AI cs.MA 88%

Distributed Interaction Graph Construction for Dynamic DCOPs in Cooperative Multi-agent Systems

Brighter Agyemang, Fenghui Ren, Jun Yan

专题命中多智能体：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

Comments Presented at PKAW 2022 (arXiv:2211.03888) Report-no: PKAW/2022/05

1. 多智能体 14943 篇

PMIC: Improving Multi-Agent Reinforcement Learning with Progressive Mutual Information Collaboration

Curiosity-driven Exploration in Sparse-reward Multi-agent Reinforcement Learning

Adversarial Deep Reinforcement Learning for Improving the Robustness of Multi-agent Autonomous Driving Policies

Efficient Communication via Self-supervised Information Aggregation for Online and Offline Multi-agent Reinforcement Learning

AIIR-MIX: Multi-Agent Reinforcement Learning Meets Attention Individual Intrinsic Reward Mixing Network

Adaptive Value Decomposition with Greedy Marginal Contribution Computation for Cooperative Multi-Agent Reinforcement Learning

Inferring Player Location in Sports Matches: Multi-Agent Spatial Imputation from Limited Observations

Learning cooperative behaviours in adversarial multi-agent systems

Low Entropy Communication in Multi-Agent Reinforcement Learning

Neural parameter calibration for large-scale multi-agent models

Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation

MA2QL: A Minimalist Approach to Fully Decentralized Multi-Agent Reinforcement Learning

Robust Multi-Agent Bandits Over Undirected Graphs

A blob method for inhomogeneous diffusion with applications to multi-agent control and sampling

Graph Neural Networks for Decentralized Multi-Agent Perimeter Defense

Decentralized Multi-agent Filtering

Counterexample Guided Abstraction Refinement with Non-Refined Abstractions for Multi-Agent Path Finding

Robust Dynamic Bus Control: A Distributional Multi-agent Reinforcement Learning Approach

Universally Expressive Communication in Multi-Agent Reinforcement Learning

Task-Oriented Data Compression for Multi-Agent Communications Over Bit-Budgeted Channels

CGIBNet: Bandwidth-constrained Communication with Graph Information Bottleneck in Multi-Agent Reinforcement Learning

Learning Individual Policies in Large Multi-agent Systems through Local Variance Minimization

Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning

AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning

Bandit approach to conflict-free multi-agent Q-learning in view of photonic implementation

JFP: Joint Future Prediction with Interactive Multi-Agent Modeling for Autonomous Driving

Distributed-Training-and-Execution Multi-Agent Reinforcement Learning for Power Control in HetNet

Heuristically Guided Compilation for Multi-Agent Path Finding

EMVLight: a Multi-agent Reinforcement Learning Framework for an Emergency Vehicle Decentralized Routing and Traffic Signal Control System

Distributed Interaction Graph Construction for Dynamic DCOPs in Cooperative Multi-agent Systems