STRATEGIC DOMINANCE AND DYNAMIC PROGRAMMING FOR MULTI-AGENT PLANNING Application to the Multi-Robot Box-pushing Problem

被引：2

作者：

Hamila, Mohamed Amine ^{[1
]}

Grislin-Le Strugeon, Emmanuelle ^{[1
]}

Mandiau, Rene ^{[1
]}

Mouaddib, Abdel-Illah

机构：

[1] Univ Valenciennes, LAMIH, Valenciennes, France

来源：

ICAART: PROCEEDINGS OF THE 4TH INTERNATIONAL CONFERENCE ON AGENTS AND ARTIFICIAL INTELLIGENCE, VOL. 2 | 2012年

关键词：

Multi-agent planning; Coordination; Stochastic games; Markov processes;

D O I：

10.5220/0003707500910097

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 planning approach for a multi-agent coordination problem in a dynamic environment. We introduce the algorithm SGInfiniteVI, allowing to apply some theories related to the engineering of multi agent systems and designed to solve stochastic games. In order to limit the decision complexity and so decreasing the used resources (memory and processor-time), our approach relies on reducing the number of joint-action at each step decision. A scenario of multi robot Box-pushing is used as a platform to evaluate and validate our approach. We show that only weakly dominated actions can improve the resolution process, despite a slight deterioration of the solution quality due to information loss,

引用

页码：91 / 97

页数：7

共 12 条

[1]

[Anonymous], 2003, Technical report

[2]

[Anonymous], 1991, Game Theory

[3] New complexity results about Nash equilibria [J].

Conitzer, Vincent ;

Sandholm, Tuomas .

GAMES AND ECONOMIC BEHAVIOR, 2008, 63 (02) :621-641

[4]

Hamila M. A., 2010, P 2010 IEEE WIC ACM, P141

[5]

Hansen EA, 2004, PROCEEDING OF THE NINETEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE SIXTEENTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE, P709

[6]

Hu J., 2003, Journal of machine learning research, V4, P1039, DOI DOI 10.1162/1532443041827880

[7]

Kearns Michael., 2000, P 16 C UNCERTAINTY A, P309

[8]

Leyton-Brown K., 2008, Synthesis Lectures on Artificial Intelligence and Machine Learning, V2, P1

[9] EQUILIBRIUM POINTS IN N-PERSON GAMES [J].

NASH, JF .

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA, 1950, 36 (01) :48-49

[10]

Neumann J. V., 1944, THEORY GAMES EC BEHA

← 1 2 →