{"id":"https://openalex.org/W2570076534","doi":"https://doi.org/10.1109/cdc.2016.7798684","title":"Symbolic method for deriving policy in reinforcement learning","display_name":"Symbolic method for deriving policy in reinforcement learning","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2570076534","doi":"https://doi.org/10.1109/cdc.2016.7798684","mag":"2570076534"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2016.7798684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7798684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://repository.tudelft.nl/file/File_707ae4c6-704f-46c9-806d-a05825fcb8fa","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017789700","display_name":"Eduard Alibekov","orcid":null},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Eduard Alibekov","raw_affiliation_strings":["Department of Cybernetics, Czech Technical University, Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Cybernetics, Czech Technical University, Prague","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004892921","display_name":"Ji\u0159\u0131\u0301 Kubal\u0131\u0301k","orcid":"https://orcid.org/0000-0002-6965-6142"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jiri Kubalik","raw_affiliation_strings":["Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University, Prague, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University, Prague, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084264842","display_name":"Robert Babu\u0161ka","orcid":"https://orcid.org/0000-0001-9578-8598"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Robert Babuska","raw_affiliation_strings":["Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University, Prague, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Robotics, and Cybernetics, Czech Technical University, Prague, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I44504214"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2789","last_page":"2795"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9922999739646912,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11663","display_name":"Viral Infectious Diseases and Gene Expression in Insects","score":0.9758999943733215,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7611235976219177},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.750977635383606},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6790500283241272},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5081808567047119},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.4992983341217041},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.49517837166786194},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.4871332347393036},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4779643714427948},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.45342469215393066},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.43885332345962524},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4310220777988434},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.4136436879634857},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34527450799942017},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23440304398536682},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2204883098602295}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7611235976219177},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.750977635383606},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6790500283241272},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5081808567047119},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4992983341217041},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.49517837166786194},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.4871332347393036},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4779643714427948},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.45342469215393066},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.43885332345962524},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4310220777988434},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.4136436879634857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34527450799942017},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23440304398536682},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2204883098602295},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cdc.2016.7798684","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2016.7798684","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"proceedings-article"},{"id":"pmh:tud:oai:tudelft.nl:uuid:086f4ffd-09e9-4033-a6f3-5c7358705052","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:086f4ffd-09e9-4033-a6f3-5c7358705052","pdf_url":"https://repository.tudelft.nl/file/File_707ae4c6-704f-46c9-806d-a05825fcb8fa","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"info:eu-repo/semantics/conferencepaper"}],"best_oa_location":{"id":"pmh:tud:oai:tudelft.nl:uuid:086f4ffd-09e9-4033-a6f3-5c7358705052","is_oa":true,"landing_page_url":"http://resolver.tudelft.nl/uuid:086f4ffd-09e9-4033-a6f3-5c7358705052","pdf_url":"https://repository.tudelft.nl/file/File_707ae4c6-704f-46c9-806d-a05825fcb8fa","source":{"id":"https://openalex.org/S4306401843","display_name":"Data Archiving and Networked Services (DANS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1322597698","host_organization_name":"Royal Netherlands Academy of Arts and Sciences","host_organization_lineage":["https://openalex.org/I1322597698"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 2016 IEEE 55th Conference on Decision and Control (CDC)","raw_type":"info:eu-repo/semantics/conferencepaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7300000190734863}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321006","display_name":"Grantov\u00e1 Agentura \u010cesk\u00e9 Republiky","ror":"https://ror.org/01pv73b02"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2570076534.pdf","grobid_xml":"https://content.openalex.org/works/W2570076534.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W197747737","https://openalex.org/W199153045","https://openalex.org/W1501347617","https://openalex.org/W1520048352","https://openalex.org/W1576818901","https://openalex.org/W1593481303","https://openalex.org/W1626155273","https://openalex.org/W1775913388","https://openalex.org/W1988505764","https://openalex.org/W2121863487","https://openalex.org/W2157208669","https://openalex.org/W2294564145","https://openalex.org/W2483158547","https://openalex.org/W2484646121","https://openalex.org/W2509705549","https://openalex.org/W4214717370","https://openalex.org/W6630229783","https://openalex.org/W6635409236","https://openalex.org/W6638085146","https://openalex.org/W6725517238"],"related_works":["https://openalex.org/W2028495302","https://openalex.org/W2002261065","https://openalex.org/W2968285896","https://openalex.org/W2808418668","https://openalex.org/W4287865573","https://openalex.org/W2025663273","https://openalex.org/W3007324819","https://openalex.org/W1574958246","https://openalex.org/W2373808749","https://openalex.org/W4387019592"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,10,14,45,66,72,96,100,131,139,146],"problem":[4],"of":[5,16,68,71,78],"deriving":[6],"a":[7,27,36,42,51,76,89,125],"policy":[8,53,91,97,127],"from":[9,49,99],"value":[11,46,103,132],"function":[12,47,59,133],"in":[13,19],"context":[15],"reinforcement":[17],"learning":[18],"continuous":[20,52,115],"state":[21],"and":[22,48,119,122,142],"input":[23,74],"spaces.":[24],"We":[25],"propose":[26],"novel":[28],"method":[29,106,129,141],"based":[30],"on":[31,110],"genetic":[32],"programming":[33],"to":[34,44,87,124],"construct":[35],"symbolic":[37,57],"function,":[38],"which":[39,50],"serves":[40],"as":[41],"proxy":[43,58],"is":[54,60],"derived.":[55],"The":[56,105,135],"constructed":[61],"such":[62],"that":[63,92,138],"it":[64],"maximizes":[65],"number":[67],"correct":[69],"choices":[70],"control":[73,90,112],"for":[75],"set":[77],"selected":[79],"states.":[80],"Maximization":[81],"methods":[82],"can":[83],"then":[84],"be":[85],"used":[86],"derive":[88],"performs":[93],"better":[94],"than":[95],"derived":[98],"original":[101],"approximate":[102],"function.":[104],"was":[107],"experimentally":[108],"evaluated":[109],"two":[111],"problems":[113],"with":[114],"spaces,":[116],"pendulum":[117],"swing-up":[118],"magnetic":[120],"manipulation,":[121],"compared":[123],"standard":[126,147],"derivation":[128],"using":[130],"approximation.":[134],"results":[136],"show":[137],"proposed":[140],"its":[143],"variants":[144],"outperform":[145],"method.":[148]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}