An Object Oriented Approach to Fuzzy Actor-Critic Learning for Multi-Agent Differential Games

被引：0
|
作者：
Schwartz, Howard [1 ]
机构：
[1] Carleton Univ, Dept Syst & Comp Engn, 1125 Colonel By Dr, Ottawa, ON, Canada
来源：
2019 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI 2019) | 2019年
关键词：
reinforcement learning; fuzzy systems; differential games; actor critic learning; multi-agent systems; CONTROLLERS;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper presents a new form of the multi-agent fuzzy actor-critic learning algorithm for differential games. An object oriented approach to defining the relationships between agents is proposed. We define the fuzzy inference system as a network structure and define attributes of the agents as rule sets that fired and rewards associated with the fired rule set. The resulting fuzzy actor-critic reinforcement learning algorithm is investigated for playing the differential pursuer super evader game. The game is played in a continuous state and action space to simulate a real world environment. All the robots in the game are simultaneously learning.
引用
收藏
页码：183 / 190
页数：8
相关论文
共 50 条
  • [21] An actor-critic approach for learning cooperative behaviors of multiagent seesaw balancing problems
    Kawakami, T
    Kinoshita, M
    Takatori, N
    Watanabe, M
    Furukawa, M
    INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOL 1-4, PROCEEDINGS, 2005, : 109 - 114
  • [22] Optimal Consensus Control for Continuous-time Multi-agent Systems via Actor-Critic Neural Networks
    Jia, Xiao
    Wolter, Katinka
    2022 8TH INTERNATIONAL CONFERENCE ON AUTOMATION, ROBOTICS AND APPLICATIONS (ICARA 2022), 2022, : 191 - 195
  • [23] Optimal Tracking Control of Heterogeneous Multi-agent Systems with Switching Topology via Actor-Critic Neural Networks
    Peng, Zhinan
    Hu, Jiangping
    Ghosh, Bijoy K.
    2018 37TH CHINESE CONTROL CONFERENCE (CCC), 2018, : 7037 - 7042
  • [24] SACHA: Soft Actor-Critic With Heuristic-Based Attention for Partially Observable Multi-Agent Path Finding
    Lin, Qiushi
    Ma, Hang
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2023, 8 (08) : 5100 - 5107
  • [25] Mutli-agent consensus under communication failure using Actor-Critic Reinforcement Learning
    Kandath, Harikumar
    Senthilnath, J.
    Sundaram, Suresh
    2018 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI), 2018, : 1461 - 1465
  • [26] An Actor-Critic Reinforcement Learning Approach for Energy Harvesting Communications Systems
    Masadeh, Ala'eddin
    Wang, Zhengdao
    Kamal, Ahmed E.
    2019 28TH INTERNATIONAL CONFERENCE ON COMPUTER COMMUNICATION AND NETWORKS (ICCCN), 2019,
  • [27] Actor-critic learning-based adaptive fuzzy controller for stepper motor
    Babu, R. Ganesh
    Chellaswamy, C.
    Geetha, T. S.
    TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL, 2023, 45 (15) : 2914 - 2932
  • [28] An Approach to Multi-Agent Pursuit Evasion Games Using Reinforcement Learning
    Bilgin, Ahmet Tunc
    Kadioglu-Urtis, Esra
    PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON ADVANCED ROBOTICS (ICAR), 2015, : 164 - 169
  • [29] MULTI-STEP ACTOR-CRITIC FRAMEWORK FOR REINFORCEMENT LEARNING IN CONTINUOUS CONTROL
    Huang T.
    Chen G.
    Journal of Applied and Numerical Optimization, 2023, 5 (02): : 189 - 200
  • [30] A Distributed Actor-Critic Learning Approach for Affine Formation Control of Multi-Robots With Unknown Dynamics
    Zhang, Ronghua
    Ma, Qingwen
    Zhang, Xinglong
    Xu, Xin
    Liu, Daxue
    INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING, 2025, : 803 - 817
12345