Learning in coaching

College

College of Computer Studies

Department/Unit

Software Technology

Document Type

Conference Proceeding

Source Title

Advances in Soft Computing

First Page

1338

Last Page

1347

Publication Date

1-1-2005

Abstract

We have developed a system (SimSoccer Coach) that shows single agent learning by analyzing the fixed opponent's behavior and then providing offensive and defensive advice to improve the team's performance. For the offensive advice, the system learns through imitation of successful passing and shooting actions of the opponent's previous games. For defensive advice, the system learns through observation of the opponent's passing behavior and thwarts any passing attempts by marking the player and intercepting the ball. To generate these sets of advice, the system reads Iogfiles of previous games played by a fixed opponent against other teams and selects the data to be used for learning. The C4.5 decision tree algorithm is used to construct the tree and generate production rules based on the selected data. These production rules are converted into CLang advice following the Coach Language grammar. These CLang rules are then given to the coachable team before the game.

html

Digitial Object Identifier (DOI)

10.1007/3-540-32391-0_136

Disciplines

Computer Sciences | Software Engineering

Keywords

Coaching (Athletics)--Computer programs

Upload File

wf_no

This document is currently not available here.

Share

COinS