{"id":"https://openalex.org/W2892053860","doi":"https://doi.org/10.1109/icra.2018.8461182","title":"Data-driven Construction of Symbolic Process Models for Reinforcement Learning","display_name":"Data-driven Construction of Symbolic Process Models for Reinforcement Learning","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2892053860","doi":"https://doi.org/10.1109/icra.2018.8461182","mag":"2892053860"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2018.8461182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033348430","display_name":"Erik Derner","orcid":"https://orcid.org/0000-0002-7588-7668"},"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":"Erik Derner","raw_affiliation_strings":["Department of Control Engineering, Czech Technical University in Prague, Prague, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Control Engineering, Czech Technical University in Prague, Prague, Czech Republic","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, Czech Technical University in Prague, Prague, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Czech Institute of Informatics, Czech Technical University in Prague, 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":["Cognitive Robotics, Faculty of 3mE, Czech Technical University in Prague, Prague, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cognitive Robotics, Faculty of 3mE, Czech Technical University in Prague, 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":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5105","last_page":"5112"},"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":0.9984999895095825,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9919999837875366,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7786715030670166},{"id":"https://openalex.org/keywords/symbolic-regression","display_name":"Symbolic regression","score":0.756496012210846},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7546747922897339},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6235118508338928},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5951557159423828},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.5944243669509888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5600637197494507},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5320010781288147},{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.5086551308631897},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5014998912811279},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4979100227355957},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.4642321467399597},{"id":"https://openalex.org/keywords/double-pendulum","display_name":"Double pendulum","score":0.41943058371543884},{"id":"https://openalex.org/keywords/inverted-pendulum","display_name":"Inverted pendulum","score":0.3584892749786377},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.2114473581314087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7786715030670166},{"id":"https://openalex.org/C2776400721","wikidata":"https://www.wikidata.org/wiki/Q18171762","display_name":"Symbolic regression","level":3,"score":0.756496012210846},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7546747922897339},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6235118508338928},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5951557159423828},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.5944243669509888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5600637197494507},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5320010781288147},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.5086551308631897},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5014998912811279},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4979100227355957},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.4642321467399597},{"id":"https://openalex.org/C167183279","wikidata":"https://www.wikidata.org/wiki/Q1243208","display_name":"Double pendulum","level":4,"score":0.41943058371543884},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.3584892749786377},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.2114473581314087},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2018.8461182","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2018.8461182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W197747737","https://openalex.org/W199153045","https://openalex.org/W326419249","https://openalex.org/W1689445748","https://openalex.org/W1949804828","https://openalex.org/W1966086707","https://openalex.org/W1979769287","https://openalex.org/W1980035368","https://openalex.org/W1996928089","https://openalex.org/W2001095967","https://openalex.org/W2023140507","https://openalex.org/W2046633936","https://openalex.org/W2056624909","https://openalex.org/W2068823081","https://openalex.org/W2103263764","https://openalex.org/W2121103318","https://openalex.org/W2121863487","https://openalex.org/W2127107099","https://openalex.org/W2131831090","https://openalex.org/W2140135625","https://openalex.org/W2289849244","https://openalex.org/W2408978589","https://openalex.org/W2509705549","https://openalex.org/W2547065907","https://openalex.org/W2570076534","https://openalex.org/W2735901402","https://openalex.org/W2766046980","https://openalex.org/W2769736739","https://openalex.org/W2950471160","https://openalex.org/W2964006217","https://openalex.org/W4211089519","https://openalex.org/W4214717370","https://openalex.org/W6607927428","https://openalex.org/W6639949747","https://openalex.org/W6656412206","https://openalex.org/W6678367057","https://openalex.org/W6679414004","https://openalex.org/W6680657880","https://openalex.org/W6696324988"],"related_works":["https://openalex.org/W2968285896","https://openalex.org/W2381504162","https://openalex.org/W1567571923","https://openalex.org/W2472646430","https://openalex.org/W2610450612","https://openalex.org/W2549153708","https://openalex.org/W2897801744","https://openalex.org/W2147355282","https://openalex.org/W2394133867","https://openalex.org/W1662819506"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"is":[3,45,92],"a":[4,21,95,114],"suitable":[5,82],"approach":[6,109,137],"for":[7,83,100,144],"controlling":[8],"systems":[9],"with":[10],"unknown":[11],"or":[12],"time-varying":[13],"dynamics.":[14],"RL":[15,49,156],"in":[16,126],"principle":[17],"does":[18],"not":[19],"require":[20],"model":[22,154],"of":[23,147],"the":[24,103,108,119,123,152,159],"system,":[25],"but":[26],"before":[27],"it":[28,33],"learns":[29],"an":[30],"acceptable":[31],"policy,":[32],"needs":[34],"many":[35],"unsuccessful":[36],"trials,":[37],"which":[38,80],"real":[39],"robots":[40],"usually":[41],"cannot":[42],"withstand.":[43],"It":[44],"well":[46],"known":[47],"that":[48,134],"can":[50,139,157],"be":[51],"sped":[52],"up":[53],"and":[54,118,128],"made":[55],"safer":[56],"by":[57,77],"using":[58],"models":[59,75,142],"learned":[60],"online.":[61],"In":[62],"this":[63,136],"paper,":[64],"we":[65,138],"propose":[66],"to":[67,71,97],"use":[68],"symbolic":[69,153],"regression":[70],"construct":[72],"compact,":[73],"parsimonious":[74],"described":[76],"analytic":[78],"equations,":[79],"are":[81],"realtime":[84],"robot":[85,117],"control.":[86],"Single":[87],"node":[88],"genetic":[89],"programming":[90],"(SNGP)":[91],"employed":[93],"as":[94],"tool":[96],"automatically":[98],"search":[99],"equations":[101],"fitting":[102],"available":[104],"data.":[105,149],"We":[106],"demonstrate":[107],"on":[110,151],"two":[111],"benchmark":[112],"examples:":[113],"simulated":[115],"mobile":[116],"pendulum":[120],"swing-up":[121],"problem;":[122],"latter":[124],"both":[125],"simulations":[127],"real-time":[129],"experiments.":[130],"The":[131],"results":[132],"show":[133],"through":[135],"find":[140],"accurate":[141],"even":[143],"small":[145],"batches":[146],"training":[148],"Based":[150],"found,":[155],"control":[158],"system":[160],"well.":[161]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}