Evolving Robocode Tank Fighters

dc.contributor.author	Eisenstein, Jacob
dc.date.accessioned	2005-12-22T01:12:20Z
dc.date.available	2005-12-22T01:12:20Z
dc.date.issued	2003-10-28
dc.identifier.other	MIT-CSAIL-TR-2003-026
dc.identifier.other	AIM-2003-023
dc.identifier.uri	http://hdl.handle.net/1721.1/30431
dc.description.abstract	In this paper, I describe the application of genetic programming to evolve a controller for a robotic tank in a simulated environment.The purpose is to explore how genetic techniques can best be applied to produce controllers based on subsumption and behavior oriented languages such as REX. As part of my implementation, I developed TableRex, a modification of REX that can be expressed on a fixed-lengthgenome. Using a fixed subsumption architecture of TableRex modules, I evolved robots that beat some of the most competitive hand-coded adversaries.
dc.format.extent	24 p.
dc.format.extent	21707085 bytes
dc.format.extent	716288 bytes
dc.format.mimetype	application/postscript
dc.format.mimetype	application/pdf
dc.language.iso	en_US
dc.relation.ispartofseries	Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory
dc.subject	AI
dc.subject	genetic programming
dc.subject	robotics
dc.title	Evolving Robocode Tank Fighters