{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T22:45:10Z","timestamp":1768430710502,"version":"3.49.0"},"reference-count":11,"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.2019.8848100","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":10,"title":["Win or Learn Fast Proximal Policy Optimisation"],"prefix":"10.1109","author":[{"given":"Dino Stephen","family":"Ratcliffe","sequence":"first","affiliation":[]},{"given":"Katja","family":"Hofmann","sequence":"additional","affiliation":[]},{"given":"Sam","family":"Devlin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","first-page":"541","article-title":"Nash convergence of gradient dynamics in general-sum games","author":"singh","year":"2000","journal-title":"UAI"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.2307\/1969529"},{"key":"ref10","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"ICLRE"},{"key":"ref6","article-title":"Openai five","year":"2018"},{"key":"ref11","article-title":"Open-ended learning in symmetric zero-sum games","author":"balduzzi","year":"2019"},{"key":"ref5","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref8","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"NIPS"},{"key":"ref7","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"ICML"},{"key":"ref2","volume":"23","author":"basar","year":"1999","journal-title":"Dynamic Noncooperative Game Theory"},{"key":"ref9","article-title":"Emergent complexity via multi-agent competition","author":"bansal","year":"2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(02)00121-2"}],"event":{"name":"2019 IEEE Conference on Games (CoG)","location":"London, United Kingdom","start":{"date-parts":[[2019,8,20]]},"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\/08848100.pdf?arnumber=8848100","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\/8848100\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":11,"URL":"https:\/\/doi.org\/10.1109\/cig.2019.8848100","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}