{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:27:55Z","timestamp":1763191675114,"version":"3.45.0"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228626","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["SPDou: Mastering the DouDiZhu Game with ISPPO Models"],"prefix":"10.1109","author":[{"given":"Shipeng","family":"Wang","sequence":"first","affiliation":[{"name":"Shenyang Aerospace University,School of Computing,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yajie","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenyang Aerospace University,School of Computing,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qilong","family":"Guo","sequence":"additional","affiliation":[{"name":"Shenyang Aerospace University,School of Computing,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shenyang Aerospace University,School of Computing,Shenyang,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Suphx: Mastering mahjong with deep reinforcement learning","year":"2020","author":"Li","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.add4679"},{"journal-title":"Horovod: fast and easy distributed deep learning in tensorflow","year":"2018","author":"Sergeev","key":"ref3"},{"journal-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","year":"2017","author":"Silver","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2022.3223926"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20394"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CyberC58899.2023.00026"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2866036"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/470"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1155\/2020\/1764594"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04281-x"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/176"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231639"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v16i1.7445"},{"key":"ref17","first-page":"12333","article-title":"Douzero: Mastering doudizhu with self-play deep reinforcement learning","volume-title":"international conference on machine learning","author":"Zha"},{"key":"ref18","first-page":"34954","article-title":"Perfectdou: Dominating doudizhu with perfect information distillation","volume":"35","author":"Yang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACAIT60137.2023.10528627"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2024.3420805"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/S0927-0507(05)80172-0","article-title":"Markov decision processes","volume":"2","author":"Puterman","year":"1990","journal-title":"Handbooks in operations research and management science"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.12794\/metadc1505267"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CAC48633.2019.8996875"},{"journal-title":"Implementation matters in deep policy gradients: A case study on ppo and trpo","year":"2020","author":"Engstrom","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IV47402.2020.9304668"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3098451"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/info11030141"},{"key":"ref28","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2023.3303251"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228626.pdf?arnumber=11228626","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:23:43Z","timestamp":1763191423000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228626\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228626","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}