Multiple Types of AI and Their Performance in Video Games

In this article, we present a comparative study of Artificial Intelligence training methods, in the context of a racing video game. The algorithms Proximal Policy Policy Optimization (PPO), Generative Adversarial Imitation Learning (GAIL) and Behavioral Cloning (BC), present in the Machine Learning...

Full description

Bibliographic Details
Main Authors: Iulian PRĂJESCU, Alina Delia CĂLIN
Format: Article
Language:English
Published: Babes-Bolyai University, Cluj-Napoca 2022-07-01
Series:Studia Universitatis Babes-Bolyai: Series Informatica
Subjects:
Online Access:http://193.231.18.162/index.php/subbinformatica/article/view/1200
_version_ 1797322260568080384
author Iulian PRĂJESCU
Alina Delia CĂLIN
author_facet Iulian PRĂJESCU
Alina Delia CĂLIN
author_sort Iulian PRĂJESCU
collection DOAJ
description In this article, we present a comparative study of Artificial Intelligence training methods, in the context of a racing video game. The algorithms Proximal Policy Policy Optimization (PPO), Generative Adversarial Imitation Learning (GAIL) and Behavioral Cloning (BC), present in the Machine Learning Agents (ML-Agents) toolkit have been used in several scenarios. We measured their learning capability and performance in terms of speed, correct level traversal, number of training steps required and we explored ways to improve their performance. These algorithms prove to be suitable for racing games and the toolkit is highly accessible within the ML-Agents toolkit. Received by the editors: 23 September 2021. 2010 Mathematics Subject Classification. 91A10, 68T05. 1998 CR Categories and Descriptors. I.2.1 [Artificial intelligence]: Applications and Expert Systems – Games; K.8.0 [Personal computing]: General – Gaming.
first_indexed 2024-03-08T05:11:39Z
format Article
id doaj.art-e980263b638448da94f13de1a4c7030c
institution Directory Open Access Journal
issn 2065-9601
language English
last_indexed 2024-03-08T05:11:39Z
publishDate 2022-07-01
publisher Babes-Bolyai University, Cluj-Napoca
record_format Article
series Studia Universitatis Babes-Bolyai: Series Informatica
spelling doaj.art-e980263b638448da94f13de1a4c7030c2024-02-07T10:03:31ZengBabes-Bolyai University, Cluj-NapocaStudia Universitatis Babes-Bolyai: Series Informatica2065-96012022-07-0167110.24193/subbi.2022.1.02Multiple Types of AI and Their Performance in Video GamesIulian PRĂJESCU0Alina Delia CĂLIN1Babes-Bolyai University, Faculty of Mathematics and Computer Science, Cluj-Napoca, Romania Email address: alina.calin@ubbcluj.roBabes-Bolyai University, Faculty of Mathematics and Computer Science, Cluj-Napoca, Romania Email address: alina.calin@ubbcluj.ro In this article, we present a comparative study of Artificial Intelligence training methods, in the context of a racing video game. The algorithms Proximal Policy Policy Optimization (PPO), Generative Adversarial Imitation Learning (GAIL) and Behavioral Cloning (BC), present in the Machine Learning Agents (ML-Agents) toolkit have been used in several scenarios. We measured their learning capability and performance in terms of speed, correct level traversal, number of training steps required and we explored ways to improve their performance. These algorithms prove to be suitable for racing games and the toolkit is highly accessible within the ML-Agents toolkit. Received by the editors: 23 September 2021. 2010 Mathematics Subject Classification. 91A10, 68T05. 1998 CR Categories and Descriptors. I.2.1 [Artificial intelligence]: Applications and Expert Systems – Games; K.8.0 [Personal computing]: General – Gaming. http://193.231.18.162/index.php/subbinformatica/article/view/1200racing game, PPO, GAIL, behavioral cloning, AI in games.
spellingShingle Iulian PRĂJESCU
Alina Delia CĂLIN
Multiple Types of AI and Their Performance in Video Games
Studia Universitatis Babes-Bolyai: Series Informatica
racing game, PPO, GAIL, behavioral cloning, AI in games.
title Multiple Types of AI and Their Performance in Video Games
title_full Multiple Types of AI and Their Performance in Video Games
title_fullStr Multiple Types of AI and Their Performance in Video Games
title_full_unstemmed Multiple Types of AI and Their Performance in Video Games
title_short Multiple Types of AI and Their Performance in Video Games
title_sort multiple types of ai and their performance in video games
topic racing game, PPO, GAIL, behavioral cloning, AI in games.
url http://193.231.18.162/index.php/subbinformatica/article/view/1200
work_keys_str_mv AT iulianprajescu multipletypesofaiandtheirperformanceinvideogames
AT alinadeliacalin multipletypesofaiandtheirperformanceinvideogames