Learning human-like behaviors using NeuroEvolution with statistical penalties

Luong Huu Phuc, Kanazawa Naoto, Kokolo Ikeda

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

3 Citations (Scopus)


In game artificial intelligence (AI), two common directions for developing non-human computer players are strong AI and human-like AI. Human-like AI aims at making computer agents behave like humans. In this direction, NeuroEvolution (NE), which is a combination of an artificial neural network (ANN) and an evolutionary algorithm (EA), had been frequently used to a make computer agent to behave like a human. Our research introduces a novel approach to create human-like computer agents in a platform game Super Mario Bros. (SMB) - we called it a 2D action game in this research. The approach utilizes statistical penalties to evaluate candidates created by NE algorithm. The penalties help in reducing mechanical actions of computer agents based on human data statistics, and the effects of statistical penalties are analyzed by asking human subjects to rate the human-likeness of agents. Experiments show that our method improves the human-likeness in the behavior of a computer agent.

Original languageEnglish
Title of host publication2017 IEEE Conference on Computational Intelligence and Games (CIG)
EditorsClare Bates Congdon, Michael Buro
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages8
ISBN (Electronic)9781538632338, 9781538632321
ISBN (Print)9781538632345
Publication statusPublished - 2017
Externally publishedYes
EventIEEE Symposium on Computational Intelligence and Games 2017 - New York, United States of America
Duration: 22 Aug 201725 Aug 2017

Publication series

Name2017 IEEE Conference on Computational Intelligence and Games, CIG 2017
ISSN (Electronic)2325-4289


ConferenceIEEE Symposium on Computational Intelligence and Games 2017
Abbreviated titleCIG 2017
Country/TerritoryUnited States of America
CityNew York
Internet address

Cite this