{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T12:34:05Z","timestamp":1730205245779,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,6,1]],"date-time":"2019-06-01T00:00:00Z","timestamp":1559347200000},"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":[[2019,6]]},"DOI":"10.1109\/cec.2019.8790001","type":"proceedings-article","created":{"date-parts":[[2019,8,8]],"date-time":"2019-08-08T20:00:07Z","timestamp":1565294407000},"page":"142-149","source":"Crossref","is-referenced-by-count":3,"title":["Deep Multi-agent Reinforcement Learning in a Common-Pool Resource System"],"prefix":"10.1109","author":[{"given":"Hanwei","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Kirley","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref38","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"ICML"},{"key":"ref33","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref32","first-page":"464","article-title":"Multi-agent reinforcement learning in sequential social dilemmas","author":"leibo","year":"2017","journal-title":"Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems"},{"key":"ref31","first-page":"3643","article-title":"A multi-agent reinforcement learning model of common-pool resource appropriation","author":"perolat","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref30","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","author":"foerster","year":"2016","journal-title":"Advances in neural information processing systems"},{"article-title":"Is multiagent deep reinforcement learning the answer or the question? a brief survey","year":"2018","author":"hernandez-leal","key":"ref37"},{"article-title":"Deep reinforcement learning: An overview","year":"2017","author":"li","key":"ref36"},{"key":"ref35","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1086\/260489"},{"key":"ref10","volume":"135","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref11","first-page":"766","article-title":"The evolution of social norms in common property resource use","author":"sethi","year":"1996","journal-title":"The American Economic Review"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-02151-y"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"mnih","key":"ref13"},{"article-title":"Continuous control with deep reinforcement learning","year":"2015","author":"lillicrap","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.092080099"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.7466396"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1126\/science.1133755"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2013.06.003"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2011.2167682"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/0303-2647(95)01551-5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/S1574-0021(05)02030-7"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0157796"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3200\/ENVT.50.4.8-21"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/537"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"682","DOI":"10.1126\/science.280.5364.682","article-title":"Extensions of the tragedy of the commons","volume":"280","author":"hardin","year":"1998","journal-title":"Science"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"journal-title":"Multi-agent Machine Learning A Reinforcement Approach","year":"2014","author":"schwartz","key":"ref7"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3998\/mpub.9739"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1038\/nature14540","article-title":"Reinforcement learning improves behaviour from evaluative feedback","volume":"521","author":"littman","year":"2015","journal-title":"Nature"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511807763"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/2001576.2001728"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1038\/nature13530"},{"key":"ref21","first-page":"2848","article-title":"Evolution of common-pool resources and social welfare in structured populations","author":"lerat","year":"0"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CEC.2010.5586328"},{"key":"ref23","first-page":"6199","article-title":"Dynamic social networks facilitate cooperation in the n-palyer prisoner’s dilemma","volume":"391","author":"nowak","year":"2012","journal-title":"Rezaei Golriz and Kirley Michael"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1098\/rspb.2015.2431"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.4337\/9781781009079.00020"}],"event":{"name":"2019 IEEE Congress on Evolutionary Computation (CEC)","start":{"date-parts":[[2019,6,10]]},"location":"Wellington, New Zealand","end":{"date-parts":[[2019,6,13]]}},"container-title":["2019 IEEE Congress on Evolutionary Computation (CEC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8778428\/8789744\/08790001.pdf?arnumber=8790001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T10:51:18Z","timestamp":1658141478000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8790001\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/cec.2019.8790001","relation":{},"subject":[],"published":{"date-parts":[[2019,6]]}}}