{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T13:40:46Z","timestamp":1730209246204,"version":"3.28.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,8,21]],"date-time":"2022-08-21T00:00:00Z","timestamp":1661040000000},"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":[[2022,8,21]]},"DOI":"10.1109\/cog51982.2022.9893661","type":"proceedings-article","created":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T19:33:31Z","timestamp":1663702411000},"page":"361-368","source":"Crossref","is-referenced-by-count":0,"title":["CaiRL: A High-Performance Reinforcement Learning Environment Toolkit"],"prefix":"10.1109","author":[{"given":"Per-Arne","family":"Andersen","sequence":"first","affiliation":[{"name":"University of Agder,Department of ICT,Grimstad,Norway"}]},{"given":"Morten","family":"Goodwin","sequence":"additional","affiliation":[{"name":"University of Agder,Department of ICT,Grimstad,Norway"}]},{"given":"Ole-Christoffer","family":"Granmo","sequence":"additional","affiliation":[{"name":"University of Agder,Department of ICT,Grimstad,Norway"}]}],"member":"263","reference":[{"article-title":"Comparing Python, Go, and C++ on the N-Queens Problem","year":"2020","author":"fua","key":"ref33"},{"key":"ref32","first-page":"1","article-title":"AI-Toolbox: A C++ library for Reinforcement Learning and Planning (with Python Bindings)","volume":"21","author":"bargiacchi","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(99)00052-1"},{"key":"ref30","first-page":"6","article-title":"Solving nonogram puzzles by reinforcement learning","volume":"34","author":"dandurand","year":"2012","journal-title":"Proceedings of the Annual Meeting of the Cognitive Science Society"},{"key":"ref10","article-title":"Model-based Reinforcement Learning: A Survey","author":"moerland","year":"2020","journal-title":"arXiv preprint arXiv 2006 16578"},{"key":"ref11","first-page":"1","article-title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning","volume":"21","author":"henderson","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref13","article-title":"The malmo platform for artificial intelligence experimentation","volume":"2016 janua","author":"johnson","year":"2016","journal-title":"IJCAI International Joint Conference on Artificial Intelligence"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref15","article-title":"DeepMind Lab","author":"beattie","year":"2016","journal-title":"arXiv preprint arXiv 1612 03801"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.scico.2021.102759"},{"key":"ref17","first-page":"1","article-title":"Towards the systematic reporting of the energy and carbon footprints of machine learning","volume":"21","author":"henderson","year":"2020","journal-title":"Journal of Machine Learning Research"},{"journal-title":"Reinforcement Learning An Introduction","year":"2018","author":"sutton","key":"ref18"},{"key":"ref19","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":"ref28","first-page":"19","article-title":"Gym-MicroRTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning","author":"huang","year":"2021","journal-title":"Proc 3rd IEEE Conference on Games may"},{"key":"ref4","first-page":"604","article-title":"Mastering Atari, Go, chess and shogi by planning with a learned model","volume":"588","author":"schrittwieser","year":"2020","journal-title":"Nature 2020 588 7839"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2017.8080435"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01758-5"},{"key":"ref6","article-title":"Reinforcement Learning in Healthcare: A Survey","author":"yu","year":"2019","journal-title":"arXiv Preprint arXiv 1908 08098"},{"key":"ref29","article-title":"Simon Tatham’s Portable Puzzle Collection","author":"bauer","year":"2021","journal-title":"Linux User Group Frankfurt Tech Rep"},{"key":"ref5","first-page":"350","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature 2019 575 7782"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2018.11.006"},{"key":"ref7","article-title":"Deep Reinforcement Learning: An Overview","author":"li","year":"2017","journal-title":"arXiv preprint arXiv 1701 07717"},{"key":"ref2","first-page":"1843","article-title":"Reinforcement Learning for Non-Stationary Markov Decision Processes: The Blessing of (More) Optimism","volume":"119","author":"cheung","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning ser Proceedings of Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2021.103535"},{"key":"ref1","first-page":"908","article-title":"Safe Model-based Reinforcement Learning with Stability Guarantees","volume":"30","author":"berkenkamp","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"55","article-title":"Efficient 2D software rendering","volume":"6","author":"mileff","year":"2012","journal-title":"Production Systems and Information Engineering"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CLUSTR.2009.5289129"},{"key":"ref21","first-page":"27","article-title":"SIMD Optimizations of Software Rendering in 2D Video Games","author":"mendel","year":"2019"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.20944\/preprints202012.0516.v1","article-title":"Comparative Analysis of C++ and Python in Terms of Memory and Time","author":"zehra","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/info11040193"},{"key":"ref26","first-page":"58","article-title":"The combinatorial multi-armed bandit problem and its application to real-time strategy games","author":"ontanon","year":"2013","journal-title":"Proceedings The Ninth AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490409"}],"event":{"name":"2022 IEEE Conference on Games (CoG)","start":{"date-parts":[[2022,8,21]]},"location":"Beijing, China","end":{"date-parts":[[2022,8,24]]}},"container-title":["2022 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9893561\/9893544\/09893661.pdf?arnumber=9893661","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:25:29Z","timestamp":1665433529000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9893661\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/cog51982.2022.9893661","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}