{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:27:51Z","timestamp":1774538871499,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100008530","name":"European Regional Development Fund under the project Robotics for Industry 4.0","doi-asserted-by":"publisher","award":["CZ.02.1.01\/0.0\/0.0\/15_003\/0000470"],"award-info":[{"award-number":["CZ.02.1.01\/0.0\/0.0\/15_003\/0000470"]}],"id":[{"id":"10.13039\/501100008530","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001824","name":"Grant Agency of the Czech Republic (GA.R) titled \u201cSymbolic Regression for Reinforcement Learning in Continuous Spaces\u201d","doi-asserted-by":"publisher","award":["15-22731S"],"award-info":[{"award-number":["15-22731S"]}],"id":[{"id":"10.13039\/501100001824","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007655","name":"Grant Agency of the Czech Technical University in Prague","doi-asserted-by":"publisher","award":["SGS19\/174\/OHK3\/3T\/13"],"award-info":[{"award-number":["SGS19\/174\/OHK3\/3T\/13"]}],"id":[{"id":"10.13039\/100007655","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3119000","type":"journal-article","created":{"date-parts":[[2021,10,10]],"date-time":"2021-10-10T22:57:43Z","timestamp":1633906663000},"page":"139697-139711","source":"Crossref","is-referenced-by-count":27,"title":["Symbolic Regression Methods for Reinforcement Learning"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6965-6142","authenticated-orcid":false,"given":"Jiri","family":"Kubalik","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7588-7668","authenticated-orcid":false,"given":"Erik","family":"Derner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3302-6779","authenticated-orcid":false,"given":"Jan","family":"Zegklitz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9578-8598","authenticated-orcid":false,"given":"Robert","family":"Babuska","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1137\/S1052623400378742"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3071178.3071271"},{"key":"ref33","first-page":"1","article-title":"Experience selection in deep reinforcement learning for control","volume":"19","author":"de bruin","year":"2018","journal-title":"J Mach Learn Res"},{"key":"ref32","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2739480.2754693"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2576768.2598291"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321743"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3390152"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2017.8264140"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2015.2428995"},{"key":"ref10","first-page":"1","article-title":"Off-policy experience retention for deep actor-critic learning","author":"de bruin","year":"2016","journal-title":"Proc Deep Reinforcement Learn Workshop Adv Neural Inf Process Syst (NIPS)"},{"key":"ref11","first-page":"1","article-title":"The impact of nondeterminism on reproducibility in deep reinforcement learning","author":"nagarajan","year":"2018","journal-title":"Proc 2nd Reproducibility Mach Learn Workshop (ICML)"},{"key":"ref40","first-page":"75","author":"hansen","year":"2006","journal-title":"The CMA evolution strategy A Comparing review"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2017.12.004"},{"key":"ref13","author":"busoniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1126\/science.1165893"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2012.06.036"},{"key":"ref16","first-page":"1","article-title":"Constructing a no-reference H. 264\/AVC bitstream-based video quality metric using genetic programming-based symbolic regression","volume":"99","author":"staelens","year":"2012","journal-title":"IEEE Trans Circuits and Syst Video Technol"},{"key":"ref17","article-title":"AI feynman: A physics-inspired method for symbolic regression","author":"udrescu","year":"2019","journal-title":"arXiv 1905 11481"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2475716"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2825236.2825239"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-20883-1_22"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1023\/A:1006559212014"},{"key":"ref27","first-page":"56","article-title":"Modelling chemical process systems using a multi-gene genetic programming algorithm","author":"hinchliffe","year":"1996","journal-title":"Late Breaking Papers"},{"key":"ref3","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2012.6252823"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3067695.3076009"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2170565"},{"key":"ref8","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":"ref7","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2010.2050586"},{"key":"ref9","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017992615625"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205578"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ifacol.2020.12.2277"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2018.09.007"},{"key":"ref24","first-page":"327","author":"jackson","year":"2012","journal-title":"Single Node Genetic Programming on Problems with Side Effects"},{"key":"ref23","first-page":"49","author":"jackson","year":"2012","journal-title":"A New Node-Focused Model for Genetic Programming"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1830483.1830557"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.5220\/0006505200910100"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2016.7798684"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09565900.pdf?arnumber=9565900","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:54Z","timestamp":1639770954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9565900\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3119000","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}