Parallel evolutionary approaches for game playing and verification using Intel Xeon Phi.

Automatic generation of artificial players is an important subject for the videogames industry. Different strategies have been proposed to implement realistic and intelligent agents for gameplaying and verification. This article presents a parallel evolutionary approach for the automation of computer player generation for video games. A learning pipeline model is defined to study the generation problem for Nintendo Entertainment System games composed of three stages: objective inference, objective refinement and artificial intelligence generation. Two case studies based on the defined pipeline are presented: an evolutionary algorithm to learn how to play the game Pinball, offloading the evaluation of the fitness function to a Xeon Phi coprocessor, and a full pipeline implementation that uses neuroevolution to generate RNNs that can play different games successfully. Results show that the proposed pipeline can be applied for the automatic generation of artificial players for the studied games. • Parallel evolutionary approaches for the automation of computer player generation for video games are introduced. • A learning pipeline model is defined to study the generation problem for Nintendo Entertainment System games. • A parallel evolutionary algorithm using Xeon Phi to learn how to play the game Pinball is presented. • A full pipeline implementation that uses neuroevolution to generate RNNs for playing different games is introduced. [ABSTRACT FROM AUTHOR]