Critic learning in multi agent credit assignment problem

被引：5

作者：

Rahaie, Zahra ^{[1
]}

Beigy, Hamid ^{[1
]}

机构：

[1] Sharif Univ Technol, Dept Comp Engn, Tehran, Iran

来源：

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS | 2016年 / 30卷 / 06期

关键词：

Multi-agent systems; credit assignment; reinforcement learning; interaction; history; knowledge; MODEL;

D O I：

10.3233/IFS-162093

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Multi-agent systems can be seen as an apparatus for testing the performance of real distributed systems. One problem encountered in multi-agent systems with the learning capability is credit assignment. This paper presents two methods for solving this problem. The first method assigns credit to the agents according to the history of the interaction while the second method assigns credit to the agents according to the knowledge of agents, and thus the shares of the agents are extracted from the feedback of the environment. The computer experiments show that critic learning has a positive impact in credit assignment problem.

引用

页码：3465 / 3480

页数：16

共 50 条

[31] Actor-Critic for Multi-Agent Reinforcement Learning with Self-Attention [J].

Zhao, Juan ;

Zhu, Tong ;

Xiao, Shuo ;

Gao, Zongqian ;

Sun, Hao .

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE, 2022, 36 (09)

[32] Multi-objective multiagent credit assignment in reinforcement learning and NSGA-II [J].

Yliniemi, Logan ;

Tumer, Kagan .

SOFT COMPUTING, 2016, 20 (10) :3869-3887

[33] Multi-objective multiagent credit assignment in reinforcement learning and NSGA-II [J].

Logan Yliniemi ;

Kagan Tumer .

Soft Computing, 2016, 20 :3869-3887

[34] Learning When to Communicate Among Actors with the Centralized Critic for the Multi-agent System [J].

Sun, Qingshuang ;

Yao, Yuan ;

Yi, Peng ;

Zhou, Xingshe ;

Yang, Gang .

COMPUTER SUPPORTED COOPERATIVE WORK AND SOCIAL COMPUTING, CHINESECSCW 2021, PT II, 2022, 1492 :134-146

[35] Structural relational inference actor-critic for multi-agent reinforcement learning [J].

Zhang, Xianjie ;

Liu, Yu ;

Xu, Xiujuan ;

Huang, Qiong ;

Mao, Hangyu ;

Carie, Anil .

NEUROCOMPUTING, 2021, 459 :383-394

[36] MULTI-AGENT REINFORCEMENT LEARNING WITH CONTRIBUTIONBASED ASSIGNMENT ONLINE ROUTING IN SDN [J].

Yue Xiaofeng ;

Wu Lijun ;

Duan Weiwei .

2022 19TH INTERNATIONAL COMPUTER CONFERENCE ON WAVELET ACTIVE MEDIA TECHNOLOGY AND INFORMATION PROCESSING (ICCWAMTIP), 2022,

[37] Signal learning with messages by reinforcement learning in multi-agent pursuit problem [J].

Noro, Kozue ;

Tenmoto, Hiroshi ;

Kamiya, Akimoto .

KNOWLEDGE-BASED AND INTELLIGENT INFORMATION & ENGINEERING SYSTEMS 18TH ANNUAL CONFERENCE, KES-2014, 2014, 35 :233-240

[38] Multi-agent actor-critic with time dynamical opponent model [J].

Tian, Yuan ;

Kladny, Klaus -Rudolf ;

Wang, Qin ;

Huang, Zhiwu ;

Fink, Olga .

NEUROCOMPUTING, 2023, 517 :165-172

[39] Credit assignment in movement-dependent reinforcement learning [J].

McDougle, Samuel D. ;

Boggess, Matthew J. ;

Crossley, Matthew J. ;

Parvin, Darius ;

Ivry, Richard B. ;

Taylor, Jordan A. .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 2016, 113 (24) :6797-6802

[40] The credit assignment problem in cortico-basal ganglia-thalamic networks: A review, a problem and a possible solution [J].

Rubin, Jonathan E. ;

Vich, Catalina ;

Clapp, Matthew ;

Noneman, Kendra ;

Verstynen, Timothy .

EUROPEAN JOURNAL OF NEUROSCIENCE, 2021, 53 (07) :2234-2253

← 1 2 3 4 5 →