{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T15:34:38Z","timestamp":1761060878063},"reference-count":23,"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.2019.8848048","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":7,"title":["MazeExplorer: A Customisable 3D Benchmark for Assessing Generalisation in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Luke","family":"Harries","sequence":"first","affiliation":[]},{"given":"Sebastian","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Jaroslaw","family":"Rzepecki","sequence":"additional","affiliation":[]},{"given":"Katja","family":"Hofmann","sequence":"additional","affiliation":[]},{"given":"Sam","family":"Devlin","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Deep reinforcement learning on a budget: 3d control and reasoning without a supercomputer","author":"beeching","year":"2019","journal-title":"arXiv 1904 01806"},{"key":"ref11","first-page":"4246","article-title":"The malmo platform for artificial intelligence experimentation","author":"johnson","year":"2016","journal-title":"IJCAI"},{"key":"ref12","article-title":"The multi-agent reinforcement learning in malmö (marlö) competition","author":"perez-liebana","year":"2019","journal-title":"arXiv 1901 08129"},{"key":"ref13","article-title":"Transfer deep reinforcement learning in 3d environments: An empirical study","author":"chaplot","year":"2016","journal-title":"NIPS Deep Reinforcemente Leaning Workshop"},{"key":"ref14","article-title":"Vizdoom competitions: playing doom from pixels","author":"wydmuch","year":"2018","journal-title":"IEEE Trans Games"},{"year":"0","author":"heiden","key":"ref15"},{"year":"0","author":"judd","key":"ref16"},{"year":"0","author":"johansson","key":"ref17"},{"year":"0","author":"software","key":"ref18"},{"journal-title":"Navdoom","year":"2018","author":"lee","key":"ref19"},{"article-title":"General video game ai: Competition, challenges and opportunities","year":"0","author":"perez-liebana","key":"ref4"},{"key":"ref3","article-title":"Procedural level generation improves generality of deep reinforcement learning","author":"justesen","year":"2018","journal-title":"arXiv preprint arXiv 1806 10729"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref8","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2018","journal-title":"arXiv 1812 02341"},{"key":"ref7","article-title":"Deepmind lab","author":"beattie","year":"2016","journal-title":"arXiv 1612 03801"},{"year":"2019","author":"gao","key":"ref2"},{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11694","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2018","journal-title":"Thirty-Second AAAI Conference on Artificial Intelligence"},{"key":"ref9","article-title":"Gotta learn fast: A new benchmark for generalization in rl","author":"nichol","year":"2018","journal-title":"arXiv 1804 03720"},{"key":"ref20","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"schulman","key":"ref21"},{"article-title":"Stable baselines","year":"2018","author":"hill","key":"ref23"}],"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\/08848048.pdf?arnumber=8848048","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,30]],"date-time":"2022-09-30T01:43:37Z","timestamp":1664502217000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8848048\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cig.2019.8848048","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}