{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T15:31:21Z","timestamp":1780500681322,"version":"3.54.1"},"reference-count":29,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"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. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1109\/tnnls.2020.3029475","type":"journal-article","created":{"date-parts":[[2020,11,4]],"date-time":"2020-11-04T20:32:21Z","timestamp":1604521941000},"page":"908-918","source":"Crossref","is-referenced-by-count":36,"title":["Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1754-1837","authenticated-orcid":false,"given":"Deheng","family":"Ye","sequence":"first","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guibin","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peilin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fuhao","family":"Qiu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8608-449X","authenticated-orcid":false,"given":"Sheng","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingfei","family":"Sun","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqian","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siqin","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Liang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenjie","family":"Lian","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bei","family":"Shi","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tengfei","family":"Shi","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiang","family":"Fu","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Yang","sequence":"additional","affiliation":[{"name":"Tencent AI Lab, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lanxiao","family":"Huang","sequence":"additional","affiliation":[{"name":"Tencent Timi Studio, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"MOBA: A new arena for game AI","volume-title":"arXiv:1705.10443","author":"do Nascimento Silva","year":"2017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011206"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref4","article-title":"Dota 2 with large scale deep reinforcement learning","volume-title":"arXiv:1912.06680","author":"Berner","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v35i4.2478"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref8","article-title":"The game imitation: Deep supervised convolutional networks for quick video game AI","volume-title":"arXiv:1702.05663","author":"Chen","year":"2017"},{"key":"ref9","article-title":"Policy distillation","volume-title":"arXiv:1511.06295","author":"Rusu","year":"2015"},{"key":"ref10","first-page":"1331","article-title":"Distilling policy distillation","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Czarnecki"},{"key":"ref11","first-page":"4965","article-title":"Learning longer-term dependencies in rnns with auxiliary losses","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Trinh"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref13","article-title":"Reinforcement learning with unsupervised auxiliary tasks","volume-title":"arXiv:1611.05397","author":"Jaderberg","year":"2016"},{"key":"ref14","first-page":"1","article-title":"Marginal policy gradients: A unified family of estimators for bounded action spaces with applications","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Eisenach"},{"key":"ref15","first-page":"6288","article-title":"Exponentially weighted imitation learning for batched historical data","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Wang"},{"key":"ref16","first-page":"2289","article-title":"Feedback-based tree search for reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Jiang"},{"key":"ref17","article-title":"MOBA-slice: A time slice based evaluation framework of relative advantage between teams in MOBA games","volume-title":"arXiv:1807.08360","author":"Yu","year":"2018"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2019.8847997"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/s0004-3702(01)00129-1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref21","first-page":"1","article-title":"Elf opengo: An analysis and open reimplementation of alphazero","volume-title":"Proc. ICML","author":"Tian"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2013.2286295"},{"key":"ref26","article-title":"StarCraft II: A new challenge for reinforcement learning","volume-title":"arXiv:1708.04782","author":"Vinyals","year":"2017"},{"key":"ref27","article-title":"Proximal policy optimization algorithms","volume-title":"arXiv:1707.06347","author":"Schulman","year":"2017"},{"key":"ref28","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"issue":"4","key":"ref29","first-page":"281","article-title":"Exact binomial confidence interval for proportions","volume":"64","author":"Morisette","year":"1998","journal-title":"Photogramm. Eng. Remote Sens."}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9722951\/09248616.pdf?arnumber=9248616","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T23:27:25Z","timestamp":1704842845000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9248616\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3]]},"references-count":29,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.3029475","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3]]}}}