Применение алгоритмов группового управления и машинного обучения на примере игры 'Battlecode'

Степанов Петр Петрович

doi:10.25136/2306-4196.2019.1.23527


	Journal Menu > Issues > Rubrics > About journal > Authors > About the Journal > Requirements for publication > Council of Editors > Peer-review process > Policy of publication. Aims & Scope. > Article retraction > Ethics > Online First Pre-Publication > Copyright & Licensing Policy > Digital archiving policy > Open Access Policy > Open access publishing costs > Article Identification Policy > Plagiarism check policy


	Journals in science databases


	About the Journal

Публикация за 72 часа - теперь это реальность!

При необходимости издательство предоставляет авторам услугу сверхсрочной полноценной публикации. Уже через 72 часа статья появляется в числе опубликованных на сайте издательства с DOI и номерами страниц.

По первому требованию предоставляем все подтверждающие публикацию документы!

MAIN PAGE > Back to contents

Cybernetics and programming

Reference:

Stepanov P.P. — Application of group control and machine learning algorithms on the example of the "Battlecode" game // Cybernetics and programming. – 2019. – № 1. – P. 75 - 82. DOI: 10.25136/2306-4196.2019.1.23527 URL: https://en.nbpublish.com/library_read_article.php?id=23527

Application of group control and machine learning algorithms on the example of the "Battlecode" game

Stepanov Petr Petrovich

Master, Far Eastern Federal University

690922, Russia, Primorskii krai, g. Vladivostok, ul. Ayaks, 10, 6011

fromuralwithlove@gmail.com

Другие публикации этого автора

DOI:

10.25136/2306-4196.2019.1.23527

Review date:

06-07-2017

Publish date:

04-03-2019

Abstract.

The subject of the research is the task of group management of autonomous agents in a dynamic multi-agent system and self-study of the management model. The author examines such aspects of the problem as a group interaction, using the example of the most effective group control algorithms, such as SWARM, ant algorithm, bee algorithm, firefly algorithm and fish school movement algorithm, and training of an artificial neural network through the use of reinforcement training. A comparison of various algorithms for finding the optimal path. The comparison was made on the basis of the gaming environment "Battlecode", which dynamically forms a new map for the new round, which ensured the quality of the comparison of the considered algorithms. The author uses statistical methods of data analysis, the selection and analysis of qualitative signs, forecasting methods, modeling method, classification method. The author shows that Q-learning increases its effectiveness by replacing the tabular representation of the Q-function with a neural network. This work proves the effectiveness of the bee algorithm in solving the problem of researching and patrolling the area. At the same time, the path search algorithm A* is much more flexible and efficient than the Dijkstra algorithm.
Keywords: multiagent system, ant algorithm, bee algorithm, game artificial intellegence, reinforcement learning, neural network, group management, Battlecode, modeling, agent
This article written in Russian. You can find full text of article in Russian here .

References

1.	Sutton R.S., Barto A.G. Reinforcement Learning. An Introduction.-The MIT Press, 1998, 322 p.
2.	Khaikin S. Neironnye seti. Polnyi kurs.-M.: Vil'yams, 2006, s. 1104.
3.	Plakhov, A. S. KRI / A. S. Plakhov // Organizatsiya razrabotki AI dlya strategicheskikh igr[Elektronnyi resurs].- 2004. Rezhim dostupa: http://masters.donntu.org/2014/fknt/kebikov/library/article6.htm
4.	Shampandar, Dzh. A. Iskustvennyi intellekt v komp'yuternykh igrakh / Dzh. A. Shampandar.-M.: Vil'yams, 2007.-768 str.
5.	V.V. Kruglov, B.V. Borisov. Iskusstvennye neironnye seti. Teoriya i praktika /-M.: Goryachaya liniya-Telekom, 2001.-382 s.
6.	K.V. Kartavtsev, O.N. Melekhova, S.V. Timchenko. Model' determinirovannoi seti robotov. // Doklady Tomskogo gosudarstvennogo universiteta sistem upravleniya i radioelektroniki – 2010, 1-1(21), 85-88 s.
7.	Barskii A.B. Logicheskie neironnye seti. M.: Binom, 2007, 352 s.
8.	L. N. Yasnitskii — Vvedenie v iskusstvennyi intellekt, 25 s.
9.	Gorbachevskaya E.N. Klassifikatsiya neironnykh setei. // Vestnik Volzhskogo universiteta im. V.N. Tatishcheva – 2012, 2(19), 35-41 s.
10.	Sokolov D.O. Primenenie dvukhetapnogo geneticheskogo programmirovaniya dlya postroeniya avtomata, upravlyayushchego model'yu tanka v igre «Robocode»[Elektronnyi resurs]. Bakalavrskaya rabota.-SPbGU ITMO, 2009. Rezhim dostupa: http://ntv.ifmo.ru/ru/article/263/primenenie_dvuhetapnogo_geneticheskogo_programmirovaniya_dlya_postroeniya_modeli_tanka_v_igre_%C2%ABROBOCODE%C2%BB.htm.
11.	Ch.I. Igorevich. Primenenie mashinnogo obucheniya dlya sozdaniya upravlyayushchikh avtomatov na primere igry Robocode.[Elektronnyi resurs], Rezhim dostupa: http://ntv.ifmo.ru/file/article/264.pdf
12.	Sandra Bleiksli, Dzheff Khokins «Ob intellekte»: Izdatel'skii dom «Vil'yams»; Moskva-Sankt-Peterburg-Kiev; 2007 ISBN ISBN 978-5-8459-1139-1 (rus.), ISBN 0-8050-7456-2 (angl.), 240 s.
13.	Novyi um korolya. O komp'yuterakh, myshlenii i zakonakh fiziki. Rodzher Penrouz, 1989. Izdatel'stvo Oksfordskogo universiteta, s. 480, ISBN: 0-19-851973-7 (1-e izd.), 402 s.
14.	Dzh. Barrat. Poslednee izobretenie chelovechestva. Iskusstvennyi intellekt i konets ery Homo sapiens. 2015, 312 s.

Link to this article

You can simply select and copy link from below text field.