{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T18:17:25Z","timestamp":1743013045596,"version":"3.28.0"},"reference-count":47,"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\/cog51982.2022.9893707","type":"proceedings-article","created":{"date-parts":[[2022,9,20]],"date-time":"2022-09-20T19:33:31Z","timestamp":1663702411000},"page":"72-79","source":"Crossref","is-referenced-by-count":2,"title":["LevDoom: A Benchmark for Generalization on Level Difficulty in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Tristan","family":"Tomilin","sequence":"first","affiliation":[{"name":"Eindhoven University of Technology,The Netherlands"}]},{"given":"Tianhong","family":"Dai","sequence":"additional","affiliation":[{"name":"Imperial College London,United Kingdom"}]},{"given":"Meng","family":"Fang","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology,The Netherlands"}]},{"given":"Mykola","family":"Pechenizkiy","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology,The Netherlands"}]}],"member":"263","reference":[{"key":"ref39","first-page":"4246","article-title":"The malmo platform for artificial intelligence experimentation","author":"johnson","year":"2016","journal-title":"International Joint Conference on Artificial Intelligence"},{"journal-title":"Quake III Arena","year":"1999","key":"ref38"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref32","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv preprint arXiv 1312 5602"},{"key":"ref31","article-title":"Babyai: A platform to study the sample efficiency of grounded language learning","author":"chevalier-boisvert","year":"2018","journal-title":"arXiv preprint arXiv 1810 08425"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2018.2877047"},{"key":"ref37","article-title":"Model-based reinforcement learning for atari","author":"kaiser","year":"2019","journal-title":"arXiv preprint arXiv 1903 00066"},{"key":"ref36","article-title":"Flatland: a lightweight first-person 2-d environment for reinforcement learning","author":"caselles-dupr\u00e9","year":"2018","journal-title":"arXiv preprint arXiv 1809 00510"},{"key":"ref35","article-title":"Ai2-thor: An interactive 3d environment for visual ai","author":"kolve","year":"2017","journal-title":"arXiv preprint arXiv 1712 05474"},{"key":"ref34","article-title":"State of the art control of atari games using shallow reinforcement learning","author":"liang","year":"2015","journal-title":"arXiv preprint arXiv 1512 01882"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1063"},{"key":"ref40","article-title":"General video game ai: a multi-track framework for evaluating agents","author":"perez-liebana","year":"2018","journal-title":"Games and Content Generation Algorithms"},{"key":"ref12","first-page":"16 495","article-title":"Deep reinforcement learning with stacked hierarchical attention for text-based games","volume":"33","author":"xu","year":"2020","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref13","first-page":"65","article-title":"Deep reinforcement learning with transformers for text adventure games","author":"xu","year":"2020","journal-title":"IEEE Conference on Games (COG)"},{"key":"ref14","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","author":"cobbe","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref15","article-title":"Off-dynamics reinforcement learning: Training for transfer with domain classifiers","author":"eysenbach","year":"2020","journal-title":"arXiv preprint arXiv 2006 13823"},{"key":"ref16","first-page":"2063","article-title":"Transfer learning for related reinforcement learning tasks via image-to-image translation","author":"gamrian","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref17","article-title":"A study on overfitting in deep reinforcement learning","author":"zhang","year":"2018","journal-title":"arXiv preprint arXiv 1804 06324"},{"key":"ref18","article-title":"Playing FPS games with deep reinforcement learning","author":"lample","year":"2016","journal-title":"arXiv preprint arXiv 1609 05284"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/339"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1613\/jair.5699"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref27","article-title":"The animal-ai environment: Training and testing animal-like artificial cognition","author":"beyret","year":"2019","journal-title":"arXiv preprint arXiv 1909 11497"},{"key":"ref6","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv preprint arXiv 1707 06347"},{"key":"ref5","article-title":"Dota 2 with large scale deep reinforcement learning","author":"berner","year":"2019","journal-title":"arXiv preprint arXiv 1912 06680"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/373"},{"key":"ref8","article-title":"Dher: Hindsight experience replay for dynamic goals","author":"fang","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref2","article-title":"Starcraft ii: A new challenge for reinforcement learning","author":"vinyals","year":"2017","journal-title":"et al"},{"key":"ref9","article-title":"Curriculum-guided hindsight experience replay","author":"fang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231802"},{"key":"ref20","article-title":"Deepmind lab","author":"beattie","year":"2016","journal-title":"arXiv preprint arXiv 1612 03801"},{"key":"ref45","article-title":"The distracting control suite–a challenging benchmark for reinforcement learning from pixels","author":"stone","year":"2021","journal-title":"arXiv preprint arXiv 2101 06286"},{"key":"ref22","first-page":"1329","article-title":"Bench-marking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref47","article-title":"Tianshou: A highly modularized deep reinforcement learning library","author":"weng","year":"2021","journal-title":"arXiv preprint arXiv 2107 14171"},{"key":"ref21","article-title":"Openai gym","author":"brockman","year":"2016","journal-title":"arXiv preprint arXiv 1606 01540"},{"key":"ref42","first-page":"1","article-title":"Maze-explorer: A customisable 3d benchmark for assessing generalisation in reinforcement learning","author":"harries","year":"2019","journal-title":"IEEE Conference on Games"},{"key":"ref24","article-title":"Generalization of reinforcement learners with working and episodic memory","author":"fortunato","year":"2019","journal-title":"arXiv preprint arXiv 1910 13406"},{"key":"ref23","article-title":"Gotta learn fast: A new benchmark for generalization in rl","author":"nichol","year":"2018","journal-title":"arXiv preprint arXiv 1804 03583"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-0208-z"},{"key":"ref44","article-title":"Alchemy: A bench-mark and analysis toolkit for meta-reinforcement learning agents","author":"wang","year":"2021","journal-title":"arXiv preprint arXiv 2102 05988"},{"key":"ref26","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","author":"cobbe","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00132"},{"key":"ref25","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"yu","year":"2020","journal-title":"Conference on Robot Learning"}],"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\/09893707.pdf?arnumber=9893707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T20:25:17Z","timestamp":1665433517000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9893707\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,21]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/cog51982.2022.9893707","relation":{},"subject":[],"published":{"date-parts":[[2022,8,21]]}}}