{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T02:44:27Z","timestamp":1769741067253,"version":"3.49.0"},"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.2019.8848075","type":"proceedings-article","created":{"date-parts":[[2019,9,26]],"date-time":"2019-09-26T21:49:14Z","timestamp":1569534554000},"page":"1-8","source":"Crossref","is-referenced-by-count":7,"title":["Rogue-Gym: A New Challenge for Generalization in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yuji","family":"Kanagawa","sequence":"first","affiliation":[]},{"given":"Tomoyuki","family":"Kaneko","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"key":"ref11","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning ICML 2015"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/373"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.07.006"},{"key":"ref14","article-title":"Auto-encoding variational Bayes","volume":"abs 1312 6114","author":"kingma","year":"2013","journal-title":"CoRR"},{"key":"ref15","first-page":"1480","article-title":"DARLA: improving zero-shot transfer in reinforcement learning","author":"higgins","year":"2017","journal-title":"Proceedings of the 34th International Conference on Machine Learning ICML 2017"},{"key":"ref16","article-title":"?-vae: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2017","journal-title":"ICLRE"},{"key":"ref17","article-title":"Deepmind lab","volume":"abs 1612 3801","author":"beattie","year":"2016","journal-title":"CoRR"},{"key":"ref18","article-title":"Openai gym","author":"brockman","year":"2016"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref4","article-title":"Quantifying generalization in reinforcement learning","volume":"abs 1812 2341","author":"cobbe","year":"2018","journal-title":"CoRR"},{"key":"ref3","article-title":"A study on overfitting in deep reinforcement learning","volume":"abs 1804 6893","author":"zhang","year":"2018","journal-title":"CoRR"},{"key":"ref6","author":"sutton","year":"2018","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref5","article-title":"Learning to drive in a day","volume":"abs 1807 412","author":"kendall","year":"2018","journal-title":"CoRR"},{"key":"ref8","article-title":"Generalization and regularization in DQN","volume":"abs 1810 123","author":"farebrother","year":"2018","journal-title":"CoRR"},{"key":"ref7","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref2","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proceedings of the 33nd International Conference on Machine Learning ICML 2016"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref9","article-title":"The arcade learning environment: An evaluation platform for general agents","volume":"abs 1207 4708","author":"bellemare","year":"2012","journal-title":"CoRR"},{"key":"ref20","article-title":"Domain adaptation for large-scale sentiment classification: A deep learning approach","author":"glorot","year":"0","journal-title":"Proceedings of the 28th International Conference on Machine Learning ICML 2011"},{"key":"ref22","first-page":"1406","article-title":"IMPALA: scalable distributed deep-rl with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"},{"key":"ref21","first-page":"5279","article-title":"Scalable trustregion method for deep reinforcement learning using Kronecker-factored approximation","author":"wu","year":"2017","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref23","first-page":"1856","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proceedings of the 35th International Conference on Machine Learning ICML 2018"}],"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\/08848075.pdf?arnumber=8848075","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,18]],"date-time":"2022-07-18T10:51:30Z","timestamp":1658141490000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8848075\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8]]},"references-count":23,"URL":"https:\/\/doi.org\/10.1109\/cig.2019.8848075","relation":{},"subject":[],"published":{"date-parts":[[2019,8]]}}}