{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:55:05Z","timestamp":1778255705199,"version":"3.51.4"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100017413","name":"Ministry of Culture and Innovation of Hungary from the National Research, Development and Innovation Fund, through the \u201cNemzeti Laborat\u00f3riumok p\u00e1ly\u00e1zati program\u201d Funding Scheme","doi-asserted-by":"publisher","award":["2022-2.1.1-NL-2022-00012"],"award-info":[{"award-number":["2022-2.1.1-NL-2022-00012"]}],"id":[{"id":"10.13039\/100017413","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3406148","type":"journal-article","created":{"date-parts":[[2024,5,27]],"date-time":"2024-05-27T17:22:54Z","timestamp":1716830574000},"page":"77501-77513","source":"Crossref","is-referenced-by-count":9,"title":["A Reinforcement Learning Approach to Military Simulations in Command: Modern Operations"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4002-3231","authenticated-orcid":false,"given":"Adonisz","family":"Dimitriu","sequence":"first","affiliation":[{"name":"Széchenyi István University, Győr, Hungary"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tam\u00e1s V.","family":"Michaletzky","sequence":"additional","affiliation":[{"name":"Széchenyi István University, Győr, Hungary"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Viktor","family":"Remeli","sequence":"additional","affiliation":[{"name":"Széchenyi István University, Győr, Hungary"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Viktor R.","family":"Tihanyi","sequence":"additional","affiliation":[{"name":"Széchenyi István University, Győr, Hungary"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv:1312.5602"},{"key":"ref2","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"Vinyals","year":"2017","journal-title":"arXiv:1708.04782"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490409"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref5","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cog52621.2021.9619076"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/15485129221083278"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5220\/0012051600003546"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231609"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2017.8123161"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/app13074569"},{"key":"ref12","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2993459"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.21659\/rupkatha.v15n4.11"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/WSC52266.2021.9715433"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1117\/12.2621242"},{"key":"ref17","article-title":"The StarCraft multi-agent challenge","author":"Samvelyan","year":"2019","journal-title":"arXiv:1902.04043"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/math11204389"},{"key":"ref19","first-page":"1","article-title":"Deep self-optimizing artificial intelligence for tactical analysis, training and optimization","volume-title":"Proc. NATO NMSG Symp., Towards Training Decis. Support Complex Multi-Domain Oper.","author":"Sommer"},{"key":"ref20","first-page":"1","article-title":"From the game map to the battlefield\u2013using deepmind\u2019s advanced alphastar techniques to support military decision-makers","volume-title":"Proc. Towards Training Decis. Support Complex Multi-Domain Oper., NATO Modeling Simulation Group (NMSG) Syposium","author":"Doll"},{"key":"ref21","first-page":"1407","article-title":"IMPALA: Scalable distributed deeP-RL with importance weighted actor-learner architectures","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Espeholt"},{"key":"ref22","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015","journal-title":"arXiv:1506.02438"},{"key":"ref23","volume-title":"Pycmo","author":"Hua","year":"2022"},{"key":"ref24","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","volume":"37","author":"Schulman"},{"key":"ref25","article-title":"Discrete and continuous action representation for practical RL in video games","author":"Delalleau","year":"2019","journal-title":"arXiv:1912.11077"},{"key":"ref26","article-title":"Hierarchical approaches for reinforcement learning in parameterized action space","author":"Wei","year":"2018","journal-title":"arXiv:1810.09656"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref28","article-title":"Efficient parallel methods for deep reinforcement learning","author":"Clemente","year":"2017","journal-title":"arXiv:1705.04862"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/s20030907"},{"key":"ref31","first-page":"151","article-title":"Understanding the impact of entropy on policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ahmed"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10540085.pdf?arnumber=10540085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T21:00:00Z","timestamp":1719349200000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10540085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3406148","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}