Proposition of multi-agent conflict situation simulation and reinforcement learning toolset with demonstration of early stage implementation

Author:

Jarosz Robert1ORCID

Affiliation:

1. Wojskowa Akademia Techniczna Wydział Cybernetyki

Abstract

This paper introduces conceptual approach to modelling conflicts. A flexible framework compatible in development phase is presented. Model scalability, possibility of parallelization and computational distribution over network is discussed. As example of application there are presented two variants of classic game theory problems. At the end of the paper current problems are briefly stated and future work direction is presented.

Publisher

Index Copernicus

Reference15 articles.

1. Mnih V., et al., “Human-level control through deep reinforcement learning”, Nature, vol. 518, no. 7540, pp. 529–533 (2015).

2. Mnih V., et al., “Asynchronous methods for deep reinforcement learning”, Proceedings of the 33rd International Conference on Machine Learning, pp. 1928–1937, NY USA 2016.

3. Lüth C., “A Review of: Human-Level Control through deep Reinforcement Learning”, Seminar Paper Artificial Intelligence for Games, University of Heidelberg 2019.

4. Bellemare M.G., Naddaf Y., Veness J., Bowling M., “The arcade learning environment: An evaluation platform for general agents”, J. Artif. Intell. Res., vol. 47, pp. 253–279 (2013).

5. Bellemare M.G., Veness J., Bowling M., “Investigating contingency awareness using Atari 2600 games”, Proceedings of the AAAI Conference on Artificial Intelligence, vol. 26(1), pp. 864–871, 2012.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3