{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T14:58:57Z","timestamp":1784127537946,"version":"3.55.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tg.2025.3588809","type":"journal-article","created":{"date-parts":[[2025,7,14]],"date-time":"2025-07-14T17:44:43Z","timestamp":1752515083000},"page":"873-892","source":"Crossref","is-referenced-by-count":20,"title":["A Comprehensive Review of Multiagent Reinforcement Learning in Video Games"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9397-2540","authenticated-orcid":false,"given":"Zhengyang","family":"Li","sequence":"first","affiliation":[{"name":"DigiPen Institute of Technology, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2248-2348","authenticated-orcid":false,"given":"Qijin","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Computational Science and Artificial Intelligence, Suzhou City University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0031-0942","authenticated-orcid":false,"given":"Xinghong","family":"Ling","sequence":"additional","affiliation":[{"name":"School of Computational Science and Artificial Intelligence, Suzhou City University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8710-1810","authenticated-orcid":false,"given":"Quan","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Soochow University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Video games remain Americas favorite pastime with more than 212 million Americans playing regularly","volume-title":"Entertainment Software Association","year":"2023"},{"key":"ref2","article-title":"Video Game Market Size, Share & Trends Analysis Report by Device (Console, Mobile, Computer), by Type (Online, Offline), by Region (Asia Pacific, North America, Europe), and Segment Forecasts, 20232030","year":"2023"},{"key":"ref3","article-title":"2024 essential facts about the U.S. video game industry","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1080\/00029890.1948.11999249"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1201\/9780429489105"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref7","article-title":"Using reinforcement learning to solve AI control problems","volume-title":"AI Game Programming Wisdom 2","author":"Manslow","year":"2004"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn.2011.6033442"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3383652.3423868"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i4.2478"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/294"},{"key":"ref14","volume-title":"Artificial Intelligence: A Modern Approach","author":"Russell","year":"2018"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref16","article-title":"Expert human-level driving in Gran Turismo Sport using deep reinforcement learning with image-based representation","author":"Imamura","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3064284"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cog57401.2023.10333194"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref24","article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tsmcc.2007.913919"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/app11114948"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2896986"},{"key":"ref30","article-title":"A survey of deep reinforcement learning in video games","author":"Shao","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/app13042443"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref33","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. 12th Int. Conf. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref34","volume-title":"An Introduction to MultiAgent Systems","author":"Wooldridge","year":"2009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.4324\/9781315151700-8"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref37","first-page":"29","article-title":"Deep recurrent Q-learning for partially observable MDPs","volume-title":"Proc. AAAI Fall Symp. Ser.","author":"Hausknecht"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref39","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Konda"},{"key":"ref40","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511811654"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref44","first-page":"242","article-title":"Multiagent reinforcement learning: Theoretical framework and an algorithm","volume-title":"Proc. 15th Int. Conf. Mach. Learn.","author":"Hu"},{"key":"ref45","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"Vinyals","year":"2017"},{"key":"ref46","article-title":"The StarCraft multi-agent challenge","author":"Samvelyan","year":"2019"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/1180875.1180898"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011206"},{"key":"ref49","first-page":"980","article-title":"Unifying temporal and structural credit assignment problems","volume-title":"Proc. 17th Int. Conf. Auton. Agents Multiagent Syst.","author":"Agogino"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.21236\/ada333248"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/203330.203343"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3049539"},{"key":"ref53","first-page":"5174","article-title":"On the utility of learning about humans for human-AI coordination","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Carroll","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cog51982.2022.9893608"},{"key":"ref55","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","volume-title":"Proc. 35th Int. Conf, Mach. Learn.","author":"Espeholt"},{"key":"ref56","article-title":"Distributed prioritized experience replay","author":"Horgan","year":"2018"},{"key":"ref57","article-title":"Make a more engaging game wML-Agents  machine learning bots for game development  reinforcement learning  Unity"},{"key":"ref58","article-title":"Reinforcement learning agents for Ubisofts Roller Champions","author":"Iskander","year":"2020"},{"key":"ref59","article-title":"MonoBehaviour.FixedUpdate","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cog51982.2022.9893628"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ssci47803.2020.9308248"},{"key":"ref62","article-title":"Lucy-SKG: Learning to play Rocket League efficiently using deep reinforcement learning","author":"Moschopoulos"},{"key":"ref63","article-title":"RLGym: Reinforcement learning in Rocket League","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cig.2016.7860433"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2877047"},{"key":"ref67","article-title":"Training agent for first-person shooter game with actor-critic curriculum learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref68","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3570945.3607305"},{"key":"ref70","first-page":"5","article-title":"Minecraft as an experimental world for AI in robotics","volume-title":"Proc. AAAI Fall Symp.","author":"Aluru"},{"key":"ref71","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2019\/339","article-title":"MineRL: A large-scale dataset of Minecraft demonstrations","author":"Guss","year":"2019"},{"key":"ref72","first-page":"4246","article-title":"The Malmo platform for artificial intelligence experimentation","volume-title":"Proc. 25th Int. Joint Conf. Artif. Intell.","author":"Johnson"},{"key":"ref73","article-title":"The Malmo Collaborative AI Challenge - Microsoft Research","year":"2022"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11581"},{"key":"ref75","article-title":"The multi-agent reinforcement learning in Malm (MARL) competition","author":"Perez-Liebana","year":"2019"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0095693"},{"key":"ref78","article-title":"AlphaStar: Mastering the real-time strategy game StarCraft II","year":"2019"},{"key":"ref79","first-page":"2570","article-title":"Grid-wise control for multi-agent reinforcement learning in video game AI","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Han"},{"key":"ref80","article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play StarCraft combat games","author":"Peng","year":"2017"},{"key":"ref81","first-page":"621","article-title":"Towards playing full MOBA games with deep reinforcement learning","volume":"33","author":"Ye","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v13i1.12938"},{"key":"ref83","doi-asserted-by":"crossref","DOI":"10.1145\/3240323.3240345","article-title":"The art of drafting: A team-oriented hero recommendation system for multiplayer online battle arena games","author":"Chen","year":"2018"},{"key":"ref84","article-title":"Acting with style: Towards designer-centred reinforcement learning for the video games industry","volume-title":"Proc. CHI Workshop Reinforcement Learn. Humans, Comput., Interaction","author":"Aytemiz","year":"2021"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782673\/11301972\/11079788.pdf?arnumber=11079788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:35:46Z","timestamp":1766082946000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11079788\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":84,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tg.2025.3588809","relation":{"has-preprint":[{"id-type":"doi","id":"10.36227\/techrxiv.173603149.94954703\/v2","asserted-by":"object"},{"id-type":"doi","id":"10.36227\/techrxiv.173603149.94954703\/v1","asserted-by":"object"}]},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}