{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:34:39Z","timestamp":1763202879466,"version":"3.37.3"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"University of Wisconsin-Madison Office of the Vice Chancellor for Research and Graduate Education funded by the Wisconsin Alumni Research Foundation"},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2041428"],"award-info":[{"award-number":["2041428"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3395249","type":"journal-article","created":{"date-parts":[[2024,4,30]],"date-time":"2024-04-30T19:50:31Z","timestamp":1714506631000},"page":"65362-65372","source":"Crossref","is-referenced-by-count":1,"title":["Comparing Reinforcement Learning and Human Learning With the Game of Hidden Rules"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-9636-6233","authenticated-orcid":false,"given":"Eric M.","family":"Pulick","sequence":"first","affiliation":[{"name":"Industrial and Systems Engineering, University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladimir","family":"Menkov","sequence":"additional","affiliation":[{"name":"Center for Discrete Mathematics and Theoretical Computer Science, Rutgers University, Piscataway, NJ, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonatan D.","family":"Mintz","sequence":"additional","affiliation":[{"name":"Industrial and Systems Engineering, University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7985-8039","authenticated-orcid":false,"given":"Paul B.","family":"Kantor","sequence":"additional","affiliation":[{"name":"Industrial and Systems Engineering, University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vicki M.","family":"Bier","sequence":"additional","affiliation":[{"name":"Industrial and Systems Engineering, University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2983871"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2886735"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2904742"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3015811"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3165074"},{"key":"ref7","article-title":"Intriguing properties of neural networks","author":"Szegedy","year":"2013","journal-title":"arXiv:1312.6199"},{"key":"ref8","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv:1412.6572"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1147\/rd.33.0210"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.215"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03051-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref18","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2884315"},{"key":"ref20","article-title":"Cooperative inverse reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"29","author":"Hadfield-Menell","year":"2016"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/hcomp.v7i1.5285"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i13.17359"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3460349"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2010.5593346"},{"key":"ref25","article-title":"The game of hidden rules: A new kind of benchmark challenge for machine learning","author":"Pulick","year":"2022","journal-title":"arXiv:2207.10218"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref27","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref29","article-title":"StarCraft II: A new challenge for reinforcement learning","author":"Vinyals","year":"2017","journal-title":"arXiv:1708.04782"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/339"},{"key":"ref31","first-page":"11881","article-title":"Honor of kings arena: An environment for generalization in competitive reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Wei","year":"2022"},{"key":"ref32","first-page":"2048","article-title":"Leveraging procedural generation to benchmark reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Cobbe"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/373"},{"key":"ref34","first-page":"7671","article-title":"The NetHack learning environment","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Kuttler","year":"2020"},{"key":"ref35","article-title":"MiniHack the planet: A sandbox for open-ended reinforcement learning research","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks","volume":"1","author":"Samvelyan"},{"key":"ref36","article-title":"The neural MMO platform for massively multiagent research","volume-title":"Neural Inf. Process. Syst. Track Datasets Benchmarks","volume":"1","author":"Suarez","year":"2021"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/978-3-030-88132-0_2","article-title":"Meta-learning","volume-title":"Automated Machine Learning and Meta-Learning for Multimedia","author":"Zhu","year":"2021"},{"key":"ref38","first-page":"1094","article-title":"Meta-world: A benchmark and evaluation for multi-task and meta reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Yu"},{"key":"ref39","article-title":"Alchemy: A benchmark and analysis toolkit for meta-reinforcement learning agents","author":"Wang","year":"2021","journal-title":"arXiv:2102.02926"},{"key":"ref40","article-title":"Reproducibility of benchmarked deep reinforcement learning tasks for continuous control","author":"Islam","year":"2017","journal-title":"arXiv:1708.04133"},{"issue":"1","key":"ref41","article-title":"Deep reinforcement learning that matters","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"32","author":"Henderson"},{"key":"ref42","article-title":"Benchmarking model-based reinforcement learning","author":"Wang","year":"2019","journal-title":"arXiv:1907.02057"},{"key":"ref43","article-title":"What matters in on-policy reinforcement learning? A large-scale empirical study","author":"Andrychowicz","year":"2020","journal-title":"arXiv:2006.05990"},{"article-title":"What matters for on-policy deep actor-critic methods? A large-scale study","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Andrychowicz","key":"ref44"},{"article-title":"Behaviour suite for reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Osband","key":"ref45"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(19)30123-2"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-016-9505-7"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1126\/science.adf6369"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-08078-3"},{"key":"ref50","article-title":"On the measure of intelligence","author":"Chollet","year":"2019","journal-title":"arXiv:1911.01547"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2022.09.002"},{"key":"ref52","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1037\/14805-009","article-title":"Amazons Mechanical Turk: A new source of inexpensive, yet high-quality, data?","volume-title":"Methodological Issues and Strategies in Clinical Research","author":"Buhrmester","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3618-5_2"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.20982\/tqmp.04.1.p013"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6287639\/10380310\/10510453-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10510453.pdf?arnumber=10510453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,18]],"date-time":"2024-05-18T04:43:17Z","timestamp":1716007397000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10510453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3395249","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}