Accession Number : ADA294084
Title : Lamarckian Learning in Multi-Agent Environments.
Corporate Author : NAVY CENTER FOR APPLIED RESEARCH IN ARTIFICIAL INTELLIGENCE WASHINGTON DC
Personal Author(s) : Grefenstette, John J.
PDF Url : ADA294084
Report Date : 1995
Pagination or Media Count : 8
Abstract : Genetic algorithms gain much of their power from mechanisms derived from the field of population genetics. However, it is possible, and in some cases desirable, to augment the standard mechanisms with additional features not available in biological systems. In this paper, we examine the use of Lamarckian learning operators in the SAMUEL architecture. The use of the operators is illustrated on three tasks in multi-agent environments. (AN)
Descriptors : *LEARNING MACHINES, *RULE BASED SYSTEMS, ALGORITHMS, SCENARIOS, OPTIMIZATION, DECISION MAKING, STRATEGY, TIME DEPENDENCE, REASONING, PROBLEM SOLVING, DECISION THEORY, HEURISTIC METHODS, ARTIFICIAL INTELLIGENCE, SYSTEMS ANALYSIS, CONTROL THEORY, SUBROUTINES, HIGH LEVEL LANGUAGES, SYMBOLIC PROGRAMMING.
Subject Categories : Cybernetics
Distribution Statement : APPROVED FOR PUBLIC RELEASE