Rule-based behavior prediction of opponent agents using Robocup 3D Soccer simulation league logfiles

Faculty / School

Faculty of Computer Sciences (FCS)

Department

Department of Computer Science

Was this content written or created while at IBA?

Yes

Document Type

Conference Paper

Publication Date

9-2012

Conference Name

IFIP International Conference on Artificial Intelligence Applications and Innovations

Conference Location

Halkidiki, Greece

Conference Dates

27-30 September 2012

ISBN/ISSN

84870812242 (Scopus)

Volume

381

First Page

285

Last Page

295

Publisher

Springer, Berlin, Heidelberg

Abstract / Description

Opponent modeling in games deals with analyzing opponents' behavior and devising a winning strategy. In this paper we present an approach to model low level behavior of individual agents using Robocup Soccer Simulation 3D environment. In 2D League, the primitive actions of agents such as Kick, Turn and Dash are known and high level behaviors are derived using these low level behaviors. In 3D League, however, the problem is complex as actions are to be inferred by observing the game. Our approach, thus, serves as a middle tier in which we learn agent behavior by means of manual data tagging by an expert and then use the rules generated by the PART algorithm to predict opponent behavior. A parser has been written for extracting data from 3D logfiles, thus making our approach generalized. Experimental results on around 6000 records of 3D league matches show very promising results.

Citation/Publisher Attribution

Larik, A. S., & Haider, S. (2012, September). Rule-based behavior prediction of opponent agents using robocup 3D soccer simulation league logfiles. In IFIP International Conference on Artificial Intelligence Applications and Innovations (pp. 285-295). Springer, Berlin, Heidelberg.

Link to Full Text

Share

COinS