Rock-Paper-Scissors WiSARD

Author

de Souza, Diego F. P. ; Carneiro, Hugo C. C. ; Franca, Felipe M. G. ; Lima, Priscila M. V.

Author_Institution

Syst. Eng. & Comput. Sci. Program - COPPE, Univ. Fed. do Rio de Janeiro, Rio de Janeiro, Brazil

fYear

2013

fDate

8-11 Sept. 2013

Firstpage

178

Lastpage

182

Abstract

This paper presents some strategies used for creating intelligent players of rock-paper-scissors using WiSARD weightless neural networks and results obtained therewith. These strategies included: (i) a new approach for encoding of the input data, (ii) three new training algorithms that allow the reclassification of the input patterns over time, (iii) a method for dealing with incomplete information in the input array, and (iv) a bluffing strategy. Experiments show that, in a tournament of intelligent agents, WiSARD-based agents were ranked among the 200 best players, one of them achieving 9th place for about three weeks.

Keywords

game theory; multi-agent systems; neural nets; WiSARD weightless neural network; WiSARD-based agent; bluffing strategy; intelligent agent; rock-paper-scissors WiSARD; training algorithm; Arrays; Equations; Games; Mathematical model; Neural networks; Random access memory; Training; Weightless neural networks; adaptiveness; bots; game; intelligent agents;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and 11th Brazilian Congress on Computational Intelligence (BRICS-CCI & CBIC), 2013 BRICS Congress on

Conference_Location

Ipojuca

Type

conf

DOI

10.1109/BRICS-CCI-CBIC.2013.38

Filename

6855847