Player profiling using hidden markov models supported with the sliding window method

Alper Kilic; Mehmet Akif Gunes; Sanem Sariel

doi:10.5220/0005711403620369

Player profiling using hidden markov models supported with the sliding window method

Alper Kilic, Mehmet Akif Gunes, Sanem Sariel

Department of Artificial Intelligence and Data Engineering

Istanbul Technical University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

In this paper, we present a player profiling system applicable for both human players and bots in video games. The Vindinium artificial intelligence (AI) contest is selected as the test-bed for analyzing the performance of our system. In this game, AI bots compete with each other in a systematically generated environment to achieve the highest score. Our profiling method is based on Hidden Markov Model (HMM) constructed by using consecutive actions of AI bots and improved with the initial training phase and our sliding window approach. The method is evaluated for three different performance criteria: recognition of bots, grouping bots that have similar game styles and tracking changes in the strategy of a single bot through the game. The results indicate that the method is promising with 90,04% binary classification success in average.

Original language	English
Title of host publication	ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence
Editors	Jaap van den Herik, Joaquim Filipe, Joaquim Filipe
Publisher	SciTePress
Pages	362-369
Number of pages	8
ISBN (Electronic)	9789897581724
DOIs	https://doi.org/10.5220/0005711403620369
Publication status	Published - 2016
Event	8th International Conference on Agents and Artificial Intelligence, ICAART 2016 - Rome, Italy Duration: 24 Feb 2016 → 26 Feb 2016

Publication series

Name	ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence
Volume	2

Conference

Conference	8th International Conference on Agents and Artificial Intelligence, ICAART 2016
Country/Territory	Italy
City	Rome
Period	24/02/16 → 26/02/16

Bibliographical note

Publisher Copyright:
Copyright © 2016 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved.

Keywords

Hidden markov model
Player profiling
Sliding window method
The vindinium game

Access to Document

10.5220/0005711403620369

Cite this

Kilic, A., Gunes, M. A., & Sariel, S. (2016). Player profiling using hidden markov models supported with the sliding window method. In J. van den Herik, J. Filipe, & J. Filipe (Eds.), ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence (pp. 362-369). (ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence; Vol. 2). SciTePress. https://doi.org/10.5220/0005711403620369

Kilic, Alper ; Gunes, Mehmet Akif ; Sariel, Sanem. / Player profiling using hidden markov models supported with the sliding window method. ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence. editor / Jaap van den Herik ; Joaquim Filipe ; Joaquim Filipe. SciTePress, 2016. pp. 362-369 (ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence).

@inproceedings{e0a81f37f66844f9959cf3abc477f126,

title = "Player profiling using hidden markov models supported with the sliding window method",

abstract = "In this paper, we present a player profiling system applicable for both human players and bots in video games. The Vindinium artificial intelligence (AI) contest is selected as the test-bed for analyzing the performance of our system. In this game, AI bots compete with each other in a systematically generated environment to achieve the highest score. Our profiling method is based on Hidden Markov Model (HMM) constructed by using consecutive actions of AI bots and improved with the initial training phase and our sliding window approach. The method is evaluated for three different performance criteria: recognition of bots, grouping bots that have similar game styles and tracking changes in the strategy of a single bot through the game. The results indicate that the method is promising with 90,04% binary classification success in average.",

keywords = "Hidden markov model, Player profiling, Sliding window method, The vindinium game",

author = "Alper Kilic and Gunes, {Mehmet Akif} and Sanem Sariel",

note = "Publisher Copyright: Copyright {\textcopyright} 2016 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved.; 8th International Conference on Agents and Artificial Intelligence, ICAART 2016 ; Conference date: 24-02-2016 Through 26-02-2016",

year = "2016",

doi = "10.5220/0005711403620369",

language = "English",

series = "ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence",

publisher = "SciTePress",

pages = "362--369",

editor = "{van den Herik}, Jaap and Joaquim Filipe and Joaquim Filipe",

booktitle = "ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence",

}

Kilic, A, Gunes, MA & Sariel, S 2016, Player profiling using hidden markov models supported with the sliding window method. in J van den Herik, J Filipe & J Filipe (eds), ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence. ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence, vol. 2, SciTePress, pp. 362-369, 8th International Conference on Agents and Artificial Intelligence, ICAART 2016, Rome, Italy, 24/02/16. https://doi.org/10.5220/0005711403620369

Player profiling using hidden markov models supported with the sliding window method. / Kilic, Alper; Gunes, Mehmet Akif; Sariel, Sanem.
ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence. ed. / Jaap van den Herik; Joaquim Filipe; Joaquim Filipe. SciTePress, 2016. p. 362-369 (ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Player profiling using hidden markov models supported with the sliding window method

AU - Kilic, Alper

AU - Gunes, Mehmet Akif

AU - Sariel, Sanem

PY - 2016

Y1 - 2016

N2 - In this paper, we present a player profiling system applicable for both human players and bots in video games. The Vindinium artificial intelligence (AI) contest is selected as the test-bed for analyzing the performance of our system. In this game, AI bots compete with each other in a systematically generated environment to achieve the highest score. Our profiling method is based on Hidden Markov Model (HMM) constructed by using consecutive actions of AI bots and improved with the initial training phase and our sliding window approach. The method is evaluated for three different performance criteria: recognition of bots, grouping bots that have similar game styles and tracking changes in the strategy of a single bot through the game. The results indicate that the method is promising with 90,04% binary classification success in average.

AB - In this paper, we present a player profiling system applicable for both human players and bots in video games. The Vindinium artificial intelligence (AI) contest is selected as the test-bed for analyzing the performance of our system. In this game, AI bots compete with each other in a systematically generated environment to achieve the highest score. Our profiling method is based on Hidden Markov Model (HMM) constructed by using consecutive actions of AI bots and improved with the initial training phase and our sliding window approach. The method is evaluated for three different performance criteria: recognition of bots, grouping bots that have similar game styles and tracking changes in the strategy of a single bot through the game. The results indicate that the method is promising with 90,04% binary classification success in average.

KW - Hidden markov model

KW - Player profiling

KW - Sliding window method

KW - The vindinium game

UR - http://www.scopus.com/inward/record.url?scp=84969195314&partnerID=8YFLogxK

U2 - 10.5220/0005711403620369

DO - 10.5220/0005711403620369

M3 - Conference contribution

AN - SCOPUS:84969195314

T3 - ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence

SP - 362

EP - 369

BT - ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence

A2 - van den Herik, Jaap

A2 - Filipe, Joaquim

PB - SciTePress

T2 - 8th International Conference on Agents and Artificial Intelligence, ICAART 2016

Y2 - 24 February 2016 through 26 February 2016

ER -

Kilic A, Gunes MA, Sariel S. Player profiling using hidden markov models supported with the sliding window method. In van den Herik J, Filipe J, Filipe J, editors, ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence. SciTePress. 2016. p. 362-369. (ICAART 2016 - Proceedings of the 8th International Conference on Agents and Artificial Intelligence). doi: 10.5220/0005711403620369

Player profiling using hidden markov models supported with the sliding window method

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this