Evolving Robocode Tank Fighters
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...
Main Author: | |
---|---|
Language: | en_US |
Published: |
2005
|
Subjects: | |
Online Access: | http://hdl.handle.net/1721.1/30431 |
_version_ | 1826216068039835648 |
---|---|
author | Eisenstein, Jacob |
author_facet | Eisenstein, Jacob |
author_sort | Eisenstein, Jacob |
collection | MIT |
description | 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. |
first_indexed | 2024-09-23T16:41:47Z |
id | mit-1721.1/30431 |
institution | Massachusetts Institute of Technology |
language | en_US |
last_indexed | 2024-09-23T16:41:47Z |
publishDate | 2005 |
record_format | dspace |
spelling | mit-1721.1/304312019-04-12T08:37:37Z Evolving Robocode Tank Fighters Eisenstein, Jacob AI genetic programming robotics 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. 2005-12-22T01:12:20Z 2005-12-22T01:12:20Z 2003-10-28 MIT-CSAIL-TR-2003-026 AIM-2003-023 http://hdl.handle.net/1721.1/30431 en_US Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory 24 p. 21707085 bytes 716288 bytes application/postscript application/pdf application/postscript application/pdf |
spellingShingle | AI genetic programming robotics Eisenstein, Jacob Evolving Robocode Tank Fighters |
title | Evolving Robocode Tank Fighters |
title_full | Evolving Robocode Tank Fighters |
title_fullStr | Evolving Robocode Tank Fighters |
title_full_unstemmed | Evolving Robocode Tank Fighters |
title_short | Evolving Robocode Tank Fighters |
title_sort | evolving robocode tank fighters |
topic | AI genetic programming robotics |
url | http://hdl.handle.net/1721.1/30431 |
work_keys_str_mv | AT eisensteinjacob evolvingrobocodetankfighters |