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

收藏

页码：3465 / 3480

页数：16

相关论文

共 50 条

[41] 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

[42] 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

[43] 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

[44] Prefrontal Neurons Encode a Solution to the Credit-Assignment Problem [J].

Asaad, Wael F. ;

Lauro, Peter M. ;

Perge, Janos A. ;

Eskandar, Emad N. .

JOURNAL OF NEUROSCIENCE, 2017, 37 (29) :6995-7007

[45] Globally Optimal Multi-agent Reinforcement Learning Parameters in Distributed Task Assignment [J].

Dahlem, Dominik ;

Harrison, William .

2009 IEEE/WIC/ACM INTERNATIONAL JOINT CONFERENCES ON WEB INTELLIGENCE (WI) AND INTELLIGENT AGENT TECHNOLOGIES (IAT), VOL 2, 2009, :28-35

[46] Distributed greedy algorithm for multi-agent task assignment problem with submodular utility functions [J].

Qu, Guannan ;

Brown, Dave ;

Li, Na .

AUTOMATICA, 2019, 105 :206-215

[47] Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning [J].

Li, Jiahui ;

Kuang, Kun ;

Wang, Baoxiang ;

Liu, Furui ;

Chen, Long ;

Wu, Fei ;

Xiao, Jun .

KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2021, :934-942

[48] An actor-critic algorithm for multi-agent learning in queue-based stochastic games [J].

Sundar, D. Krishna ;

Ravikumar, K. .

NEUROCOMPUTING, 2014, 127 :258-265

[49] A Study for Comparative Analysis of Dueling DQN and Centralized Critic Approaches in Multi-Agent Reinforcement Learning [J].

Sugimoto, Masashi ;

Hasegawa, Kaito ;

Ishida, Yuuki ;

Ohnishi, Rikuto ;

Nakagami, Kouki ;

Tsuzuki, Shinji ;

Urushihara, Shiro ;

Sori, Hitoshi .

JOURNAL OF ROBOTICS AND MECHATRONICS, 2024, 36 (03) :589-602

[50] Cluster Assignment in Multi-Agent Systems [J].

Sharf, Miel ;

Zelazo, Daniel .

2022 13TH ASIAN CONTROL CONFERENCE, ASCC, 2022, :947-952

← 1 2 3 4 5 →