{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T12:22:27Z","timestamp":1764937347320,"version":"3.28.0"},"reference-count":81,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,8,17]],"date-time":"2021-08-17T00:00:00Z","timestamp":1629158400000},"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":[[2021,8,17]]},"DOI":"10.1109\/cog52621.2021.9619000","type":"proceedings-article","created":{"date-parts":[[2021,12,7]],"date-time":"2021-12-07T20:53:06Z","timestamp":1638910386000},"page":"01-08","source":"Crossref","is-referenced-by-count":7,"title":["Procedural Content Generation: Better Benchmarks for Transfer Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Matthias","family":"Muller-Brockhausen","sequence":"first","affiliation":[{"name":"Leiden Institute of Advanced Computer Science Leiden University,The Netherlands"}]},{"given":"Mike","family":"Preuss","sequence":"additional","affiliation":[{"name":"Leiden Institute of Advanced Computer Science Leiden University,The Netherlands"}]},{"given":"Aske","family":"Plaat","sequence":"additional","affiliation":[{"name":"Leiden Institute of Advanced Computer Science Leiden University,The Netherlands"}]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.bica.2018.09.003"},{"journal-title":"R12 Fast reinforcement learning via slow reinforcement learning","year":"2016","author":"duan","key":"ref72"},{"journal-title":"A framework for reinforcement learning and planning","year":"2020","author":"moerland","key":"ref71"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"journal-title":"Alchemy A structured task distribution for meta-reinforcement learning","year":"2021","author":"wang","key":"ref76"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CoG47356.2020.9231705"},{"key":"ref39","article-title":"Illuminating generalization in deep reinforcement learning through procedural level generation","author":"justesen","year":"2018","journal-title":"ArXiv Preprint"},{"journal-title":"Evolutionarily-curated curriculum learning for deep reinforcement learning agents","year":"2019","author":"green","key":"ref74"},{"key":"ref38","article-title":"Leveraging procedural generation to benchmark reinforcement learning","author":"cobbe","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref75","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","author":"yu","year":"0","journal-title":"Conference on Robot Learning"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CoG52621.2021.9619053"},{"journal-title":"Emergent Tool Use From Multi-Agent Autocurricula","year":"2020","author":"baker","key":"ref79"},{"key":"ref33","first-page":"2063","article-title":"Transfer learning for related reinforcement learning tasks via image-to-image translation","author":"gamrian","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/artl.2009.15.2.15202"},{"key":"ref31","first-page":"36","article-title":"Vpe: Variational policy embedding for transfer reinforcement learning","author":"arnekvist","year":"0","journal-title":"2019 International Conference on Robotics and Automation (ICRA)"},{"journal-title":"Continual reinforcement learning deployed in real-life using policy distillation and sim2real transfer","year":"2019","author":"traor\u00e9","key":"ref30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5120\/15411-3885"},{"key":"ref36","first-page":"385","article-title":"Finding structure in reinforcement learning","volume":"7","author":"schwartz","year":"1995","journal-title":"Advances in neural information processing systems"},{"journal-title":"Elements of Machine Learning","year":"1995","author":"langley","key":"ref35"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref62","first-page":"1480","article-title":"Darla: Improving zero-shot transfer in reinforcement learning","author":"higgins","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref61","first-page":"1822","article-title":"Learning to search with mctsnets","author":"guez","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref28","article-title":"Knowledge transfer for deep reinforcement learning with hierarchical experience replay","volume":"31","author":"yin","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2971172"},{"journal-title":"Transferring task goals via hierarchical reinforcement learning","year":"2018","author":"xie","key":"ref27"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2952353"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341260"},{"journal-title":"A distributed reinforcement learning solution with knowledge transfer capability for a bike rebalancing problem","year":"2018","author":"xiao","key":"ref29"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.29007\/m4db"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555955"},{"key":"ref2","article-title":"Dota 2 with large scale deep reinforcement learning","volume":"abs 1912 6680","author":"berner","year":"2019","journal-title":"CoRR"},{"key":"ref69","article-title":"An automated measure of mdp similarity for transfer in reinforcement learning","author":"ammar","year":"0","journal-title":"Workshops at the Twenty-Eighth AAAI Conference on Artificial Intelligence 2014"},{"key":"ref1","article-title":"Carbon emissions and large neural network training","author":"patterson","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0098679"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-020-00146-7"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2016.01.030"},{"key":"ref24","article-title":"Transfer learning for reinforcement learning on a physical robot","volume":"1","author":"barrett","year":"0","journal-title":"Ninth International Conference on Autonomous Agents and Multiagent Systems-Adaptive Learning Agents Workshop (AAMAS-ALA)"},{"journal-title":"Integrating policy transfer policy reuse and experience replay in speeding up reinforcement learning of the obstacle avoidance task","year":"2014","author":"miriti","key":"ref23"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JETCAS.2019.2932285"},{"journal-title":"Using cases as heuristics in reinforcement learning a transfer learning application","year":"2011","author":"celiberto","key":"ref25"},{"key":"ref50","first-page":"1329","article-title":"Bench-marking deep reinforcement learning for continuous control","author":"duan","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref58","first-page":"895","article-title":"Building portable options: Skill transfer in reinforcement learning","volume":"7","author":"konidaris","year":"2007","journal-title":"IJCAI"},{"key":"ref57","article-title":"Trans-fer reinforcement learning across environment dynamics with multiple advisors","author":"plisnier","year":"0","journal-title":"BNAIC\/BENELEARN 2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_41"},{"key":"ref55","first-page":"1193","article-title":"Transfer-ring experience in reinforcement learning through task decomposition","author":"partalas","year":"2009","journal-title":"AAMAS (2)"},{"key":"ref54","first-page":"494","article-title":"Using homomorphisms to transfer options across continuous reinforcement learning domains","volume":"6","author":"soni","year":"2006","journal-title":"AAAI"},{"key":"ref53","article-title":"Unsupervised cross-domain transfer in policy gradient reinforcement learning via manifold alignment","volume":"29","author":"ammar","year":"0","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8462977"},{"key":"ref10","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"narvekar","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/electronics9091363"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2664665"},{"journal-title":"Transfer Learning in Deep Reinforcement Learning A Survey","year":"2020","author":"zhu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2740908.2742839"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30796-7_8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/S1472669614000255"},{"journal-title":"Single episode policy transfer in reinforcement learning","year":"2020","author":"yang","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/430"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2019.2901021"},{"journal-title":"Automated Transfer in Reinforcement Learning","year":"2013","author":"ammar","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/2008\/10\/P10008"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40994-3_46"},{"journal-title":"Interactive website to explore the data presented in this paper","year":"2021","author":"m\u00fcller-brockhausen","key":"ref4"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grand-master level in starcraft ii using multi-agent reinforcement learning","volume":"575","author":"vinyals","year":"2019","journal-title":"Nature"},{"key":"ref6","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"Journal of Machine Learning Research"},{"journal-title":"A survey of transfer learning methods for reinforcement learning","year":"2008","author":"bone","key":"ref5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_5"},{"key":"ref49","article-title":"Airsim: High-fidelity visual and physical simulation for autonomous vehicles","author":"shah","year":"2017","journal-title":"Field and Service Robotics"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v32i1.2329"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11396"},{"key":"ref46","article-title":"Reproducibility, reusability, and robustness in deep reinforcement learning","author":"pineau","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref45","article-title":"Iclr reproducibility challenge","volume":"5","author":"pineau","year":"2019","journal-title":"ReScience C"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"journal-title":"OpenAI Gym","year":"2016","author":"brockman","key":"ref47"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11263"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.29007\/qwpk"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1117\/12.2559546"}],"event":{"name":"2021 IEEE Conference on Games (CoG)","start":{"date-parts":[[2021,8,17]]},"location":"Copenhagen, Denmark","end":{"date-parts":[[2021,8,20]]}},"container-title":["2021 IEEE Conference on Games (CoG)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9618888\/9618891\/09619000.pdf?arnumber=9619000","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:14:11Z","timestamp":1659485651000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9619000\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,17]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/cog52621.2021.9619000","relation":{},"subject":[],"published":{"date-parts":[[2021,8,17]]}}}