{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:20:09Z","timestamp":1766067609236,"version":"3.37.3"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012492","name":"Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012492","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,8,21]]},"DOI":"10.1109\/cog51982.2022.9893608","type":"proceedings-article","created":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T19:33:31Z","timestamp":1663702411000},"page":"229-236","source":"Crossref","is-referenced-by-count":3,"title":["Mastering the Game of 3v3 Snakes with Rule-Enhanced Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Jitao","family":"Wang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Dongyun","family":"Xue","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Hefei,China"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center,Hefei,China"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Institute of Artificial Intelligence Hefei Comprehensive Nation Science Center,Hefei,China"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref11","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017","journal-title":"arXiv preprint arXiv 1707 02209"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref12"},{"key":"ref13","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proceedings of the International Conference on Machine Learning (ICML)"},{"key":"ref14","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv Learning"},{"key":"ref15","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"1992","journal-title":"Machine Learning"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/AGENTS.2018.8460004"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/science.aay2400"},{"key":"ref3","article-title":"Suphx: Mastering mahjong with deep reinforcement learning","author":"li","year":"2020","journal-title":"arXiv preprint arXiv 2003 13874"},{"key":"ref6","article-title":"The StarCraft Multi-Agent Challenge","volume":"abs 1902 4043","author":"samvelyan","year":"2019","journal-title":"CoRR"},{"key":"ref5","first-page":"576","article-title":"Mastering fighting game using deep reinforcement learning with self-play","author":"kim","year":"2020","journal-title":"Proceedings of the IEEE Conference on Games (CoG)"},{"key":"ref8","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019","journal-title":"arXiv preprint arXiv 1912 06680"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/SIEDS49339.2020.9106686"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619124"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grand-master level in starcraft ii using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/PuneCon46936.2019.9105796"},{"key":"ref22","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CSCI49370.2019.00073"}],"event":{"name":"2022 IEEE Conference on Games (CoG)","start":{"date-parts":[[2022,8,21]]},"location":"Beijing, China","end":{"date-parts":[[2022,8,24]]}},"container-title":["2022 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9893561\/9893544\/09893608.pdf?arnumber=9893608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:25:35Z","timestamp":1665433535000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9893608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/cog51982.2022.9893608","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}