Analysing Congestion Problems in Multi-agent Reinforcement Learning

被引：0
|
作者：
Radulescu, Roxana [1 ]
Vrancx, Peter [1 ]
Nowe, Ann [1 ]
机构：
[1] Vrije Univ Brussel, Brussels, Belgium
来源：
AAMAS'17: PROCEEDINGS OF THE 16TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS | 2017年
关键词：
Multi-agent reinforcement learning; Congestion problems; Resource abstraction;
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
We extend the study of congestion problems to a more realistic scenario, the Road Network Domain (RND), where the resources are no longer independent, but rather part of a network, thus choosing one path will also impact the load of another one having common road segments. We demonstrate the application of state-of-the-art multi-agent reinforcement learning methods for this new congestion model and analyse their performance. RND allows us to highlight an important limitation of resource abstraction and show that the difference rewards approach manages to better capture and inform the agents about the dynamics of the environment.
引用
收藏
页码：1705 / 1707
页数：3
相关论文
共 50 条
  • [1] Multi-Agent Reinforcement Learning
    Stankovic, Milos
    2016 13TH SYMPOSIUM ON NEURAL NETWORKS AND APPLICATIONS (NEUREL), 2016, : 43 - 43
  • [2] Important Scientific Problems of Multi-Agent Deep Reinforcement Learning
    Sun C.-Y.
    Mu C.-X.
    Zidonghua Xuebao/Acta Automatica Sinica, 2020, 46 (07): : 1301 - 1312
  • [3] Classes of Dilemma Problems and Their Multi-Agent Reinforcement Learning Method
    Kuroe, Yasuaki
    Iima, Hitoshi
    IEEE ACCESS, 2024, 12 : 107353 - 107367
  • [4] Multi-Agent Cognition Difference Reinforcement Learning for Multi-Agent Cooperation
    Wang, Huimu
    Qiu, Tenghai
    Liu, Zhen
    Pu, Zhiqiang
    Yi, Jianqiang
    Yuan, Wanmai
    2021 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2021,
  • [5] Multi-Agent Reinforcement Learning With Distributed Targeted Multi-Agent Communication
    Xu, Chi
    Zhang, Hui
    Zhang, Ya
    2023 35TH CHINESE CONTROL AND DECISION CONFERENCE, CCDC, 2023, : 2915 - 2920
  • [6] Multi-Agent Uncertainty Sharing for Cooperative Multi-Agent Reinforcement Learning
    Chen, Hao
    Yang, Guangkai
    Zhang, Junge
    Yin, Qiyue
    Huang, Kaiqi
    2022 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2022,
  • [7] Hierarchical multi-agent reinforcement learning
    Mohammad Ghavamzadeh
    Sridhar Mahadevan
    Rajbala Makar
    Autonomous Agents and Multi-Agent Systems, 2006, 13 : 197 - 229
  • [8] Learning to Share in Multi-Agent Reinforcement Learning
    Yi, Yuxuan
    Li, Ge
    Wang, Yaowei
    Lu, Zongqing
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [9] Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning
    Castellini, Jacopo
    Oliehoek, Frans A.
    Savani, Rahul
    Whiteson, Shimon
    AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS, 2021, 35 (02)
  • [10] Analysing factorizations of action-value networks for cooperative multi-agent reinforcement learning
    Jacopo Castellini
    Frans A. Oliehoek
    Rahul Savani
    Shimon Whiteson
    Autonomous Agents and Multi-Agent Systems, 2021, 35
12345