{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:49:48Z","timestamp":1729637388450,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,8,1]],"date-time":"2020-08-01T00:00:00Z","timestamp":1596240000000},"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":[[2020,8]]},"DOI":"10.1109\/cog47356.2020.9231530","type":"proceedings-article","created":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T14:05:50Z","timestamp":1603289150000},"page":"423-430","source":"Crossref","is-referenced-by-count":1,"title":["Evaluating Generalisation in General Video Game Playing"],"prefix":"10.1109","author":[{"given":"Martin","family":"Balla","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Simon M.","family":"Lucas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Diego","family":"Perez-Liebana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"year":"2016","author":"mnih","article-title":"Asynchronous methods for deep reinforcement learning","key":"ref10"},{"key":"ref11","article-title":"Training agent for first-person shooter game with actor-critic curriculum learning","author":"wu","year":"2017","journal-title":"ICLRE"},{"key":"ref12","article-title":"Clyde: A deep reinforcement learning doom playing agent","author":"ratcliffe","year":"2017","journal-title":"Workshops at the Thirtieth AAAI Conference on Artificial Intelligence"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v31i1.10916","article-title":"The option-critic architecture","author":"bacon","year":"2017","journal-title":"Thirty-First AAAI Conference on Artificial Intelligence"},{"year":"0","author":"jaderberg","article-title":"Reinforcement learning with unsupervised auxiliary tasks","key":"ref14"},{"year":"2017","author":"schulman","article-title":"Proximal policy optimization algorithms","key":"ref15"},{"year":"2018","author":"espeholt","article-title":"Impala: Scalable distributed deep-rl with importance weighted actor-learner architectures","key":"ref16"},{"key":"ref17","article-title":"Generalization and regularization in dqn","author":"farebrother","year":"2018","journal-title":"arXiv preprint 1810 00123"},{"key":"ref18","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref19","article-title":"Leveraging procedural generation to benchmark reinforcement learning","author":"cobbe","year":"2019","journal-title":"arXiv preprint arXiv 1912 01588"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/CIG.2013.6633610"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.24963\/ijcai.2019\/373"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/TG.2019.2901021"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TCIAIG.2015.2402393"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1613\/jair.3912"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1109\/CIG.2018.8490422"},{"year":"2018","author":"nichol","article-title":"Gotta learn fast: A new benchmark for generalization in rl","key":"ref2"},{"key":"ref1","article-title":"Illuminating generalization in deep reinforcement learning through procedural level generation","author":"justesen","year":"2018","journal-title":"arXiv preprint arXiv 1806 10729"},{"key":"ref9","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"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CIG.2015.7317943"},{"key":"ref22","article-title":"Illuminating Generalization in Deep Reinforcement Learning through Procedural Level Generation","author":"justesen","year":"2018","journal-title":"arXiv 1806 10729"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/CEC.2017.7969556"},{"year":"2018","author":"hessel","article-title":"Multi-task deep reinforcement learning with popart","key":"ref24"},{"key":"ref23","first-page":"4287","article-title":"Learning values across many orders of magnitude","author":"van hasselt","year":"2016","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2020 IEEE Conference on Games (CoG)","start":{"date-parts":[[2020,8,24]]},"location":"Osaka, Japan","end":{"date-parts":[[2020,8,27]]}},"container-title":["2020 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9222389\/9231525\/09231530.pdf?arnumber=9231530","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T00:22:04Z","timestamp":1669249324000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9231530\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/cog47356.2020.9231530","relation":{},"subject":[],"published":{"date-parts":[[2020,8]]}}}