Title :
Neural Network Approximations of Solution Concepts for Multiagent Coalitions
Author :
Leon, Florin ; Burlacu, Andrei Marius
Author_Institution :
Fac. of Autom. Control & Comput. Eng., Gheorghe Asachi Tech. Univ. of Iasi, Iasi, Romania
Abstract :
Coalition formation is an important aspect of multiagent systems because it enables agents to achieve goals more efficiently or goals they cannot accomplish individually. In this paper we consider an approximate method based on neural networks to estimate two important values used for dividing the payoff of a coalition, namely the Shapley value and the nucleolus. We try several neural network topologies and different training algorithms and evaluate the behavior of an especially designed multiagent system when the payoff values are computed by exact and approximate methods.
Keywords :
approximation theory; learning (artificial intelligence); multi-agent systems; neural nets; Shapley value; coalition formation; multiagent coalitions; neural network approximations; nucleolus; solution concepts; training algorithms; Distributed computing; Shapley value; coalitions; cooperative games; multiagent system; neural networks; nucleolus;
Conference_Titel :
Parallel and Distributed Computing (ISPDC), 2013 IEEE 12th International Symposium on
Conference_Location :
Bucharest
Print_ISBN :
978-1-4799-2967-2
DOI :
10.1109/ISPDC.2013.36