{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T10:23:58Z","timestamp":1758191038750,"version":"3.44.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":[[2025,9]]},"DOI":"10.1109\/tg.2025.3546252","type":"journal-article","created":{"date-parts":[[2025,2,27]],"date-time":"2025-02-27T13:57:09Z","timestamp":1740664629000},"page":"787-796","source":"Crossref","is-referenced-by-count":0,"title":["Mini <i>Honor of Kings<\/i>: A Lightweight Environment for Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"17","author":[{"given":"Lin","family":"Liu","sequence":"first","affiliation":[{"name":"Technology of China, University of Science, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4895-990X","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Polixir, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Hu","sequence":"additional","affiliation":[{"name":"Telecommunications, Beijing University of Posts, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengtao","family":"Cao","sequence":"additional","affiliation":[{"name":"Polixir, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youpeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"Polixir, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenbin","family":"Ye","sequence":"additional","affiliation":[{"name":"Tencent Timi Studio, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Meng","sequence":"additional","affiliation":[{"name":"Tencent Timi Studio, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent Timi Studio, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3433-8435","authenticated-orcid":false,"given":"Zhaofeng","family":"He","sequence":"additional","affiliation":[{"name":"Telecommunications, Beijing University of Posts, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Technology of China, University of Science, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xia","family":"Lin","sequence":"additional","affiliation":[{"name":"Tencent Timi Studio, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lanxiao","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent Timi Studio, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v33i3.2426"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2997896"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2019.2931830"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.1900661"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2019.103216"},{"key":"ref11","first-page":"15032","article-title":"Pettingzoo: Gym for multi-agent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Terry","year":"2021"},{"key":"ref12","first-page":"2186","article-title":"The starcraft multi-agent challenge","volume-title":"Proc. Int. Joint Conf. Auton. Agents Multiagent Syst.","author":"Samvelyan","year":"2019"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3095264"},{"key":"ref15","first-page":"11881","article-title":"Honor of Kings arena: An environment for generalization in competitive reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wei","year":"2022"},{"article-title":"Hok3v3: An environment for generalization in heterogeneous multi-agent reinforcement learning","year":"2023","author":"Liu","key":"ref16"},{"article-title":"Openspiel: A framework for reinforcement learning in Games","year":"2019","author":"Lanctot","key":"ref17"},{"key":"ref18","first-page":"1","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref19","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3232390"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3310150"},{"key":"ref22","article-title":"Trust region policy optimisation in multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kuba","year":"2022"},{"article-title":"Deep multi-agent reinforcement learning for decentralized continuous cooperative control","year":"2020","author":"Witt","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"article-title":"Starcraft II: A new challenge for reinforcement learning","year":"2017","author":"Vinyals","key":"ref25"},{"key":"ref26","article-title":"Rethinking the implementation tricks and monotonicity constraint in cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu","year":"2021"},{"key":"ref27","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"Proc. Int. Conf. Auton. Agents MultiAgent Syst.","author":"Sunehag","year":"2018"},{"key":"ref28","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid","year":"2018"},{"article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","year":"2020","author":"Yang","key":"ref29"},{"article-title":"Smac-hard: Enabling mixed opponent strategy script and self-play on SMAC","year":"2024","author":"Deng","key":"ref30"},{"key":"ref31","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.2514\/6.2021-1860"},{"article-title":"Cooperative multi-agent transfer learning with level-adaptive credit assignment","year":"2021","author":"Zhou","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/65"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/e23081043"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3108237"},{"key":"ref37","first-page":"6826","article-title":"Cooperative exploration for multi-agent deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Liu","year":"2021"},{"key":"ref38","first-page":"10041","article-title":"Maser: Multi-agent reinforcement learning with subgoals generated from experience replay buffer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jeon","year":"2022"},{"key":"ref39","first-page":"61759","article-title":"Hierarchical multi-agent skill discovery","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2024"},{"key":"ref40","article-title":"On the utility of learning about humans for human-ai coordination","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Carroll","year":"2019"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7782673\/11165227\/10906461.pdf?arnumber=10906461","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T05:00:00Z","timestamp":1758085200000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10906461\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":40,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tg.2025.3546252","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}