Deep Boltzmann Machine for evolutionary agents of Mario AI

Author

Hisashi, Handa

Author_Institution

Kindai Univ., Higashi-Osaka, Japan

fYear

2014

fDate

6-11 July 2014

Firstpage

36

Lastpage

41

Abstract

Deep Learning has attracted much attention recently since it can extract features taking account into the high-order knowledge. In this paper, we examine the Deep Boltzmann Machines for scene information of the Mario AI Championship. That is, the proposed method is composed of two parts: the DBM and a recurrent neural network. The DBM extracts features behind perceptual scene information, and it learns off-line. On the other hand, the recurrent neural network utilizes features to decide actions of the Mario AI agents, and it learns on-line by using Particle Swarm Optimization. Experimental results show the effectiveness of the proposed method.

Keywords

Boltzmann machines; evolutionary computation; feature extraction; learning (artificial intelligence); multi-agent systems; particle swarm optimisation; recurrent neural nets; DBM; Mario AI Championship; Mario AI agents; deep Boltzmann machine; deep learning; evolutionary agents; feature extraction; high-order knowledge; particle swarm optimization; recurrent neural network; Artificial intelligence; Artificial neural networks; Feature extraction; Games; Neurons; Recurrent neural networks; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation (CEC), 2014 IEEE Congress on

Conference_Location

Beijing

Print_ISBN

978-1-4799-6626-4

Type

conf

DOI

10.1109/CEC.2014.6900625

Filename

6900625