{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T16:34:58Z","timestamp":1762014898316,"version":"build-2065373602"},"reference-count":10,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T00:00:00Z","timestamp":1564617600000},"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":[[2019,8]]},"DOI":"10.1109\/cig.2019.8848014","type":"proceedings-article","created":{"date-parts":[[2019,9,27]],"date-time":"2019-09-27T01:49:14Z","timestamp":1569548954000},"page":"1-4","source":"Crossref","is-referenced-by-count":4,"title":["A Self-Play Policy Optimization Approach to Battling Pok\u00e9mon"],"prefix":"10.1109","author":[{"given":"Dan","family":"Huang","sequence":"first","affiliation":[]},{"given":"Scott","family":"Lee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Technical machine","year":"0","author":"stone","key":"ref4"},{"year":"2019","key":"ref3","article-title":"pmariglia\/showdown"},{"year":"2013","key":"ref10","article-title":"Resource - everything you ever wanted to know about ratings"},{"key":"ref6","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Advances in neural information processing systems"},{"year":"0","key":"ref5","article-title":"Openai five"},{"key":"ref8","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":"ref7","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"CoRR"},{"year":"2016","key":"ref2","article-title":"vasumv\/pokemon ai"},{"journal-title":"The Glicko System","year":"1995","author":"glickman","key":"ref9"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080435"}],"event":{"name":"2019 IEEE Conference on Games (CoG)","start":{"date-parts":[[2019,8,20]]},"location":"London, United Kingdom","end":{"date-parts":[[2019,8,23]]}},"container-title":["2019 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8844551\/8847948\/08848014.pdf?arnumber=8848014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T14:51:30Z","timestamp":1658155890000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8848014\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":10,"URL":"https:\/\/doi.org\/10.1109\/cig.2019.8848014","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}