{"id":"https://openalex.org/W2961374456","doi":"https://doi.org/10.1145/3319619.3326755","title":"Generating interpretable reinforcement learning policies using genetic programming","display_name":"Generating interpretable reinforcement learning policies using genetic programming","publication_year":2019,"publication_date":"2019-07-10","ids":{"openalex":"https://openalex.org/W2961374456","doi":"https://doi.org/10.1145/3319619.3326755","mag":"2961374456"},"language":"en","primary_location":{"id":"doi:10.1145/3319619.3326755","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3319619.3326755","pdf_url":null,"source":{"id":"https://openalex.org/S4363608771","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"},"type":"article","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/A5060543628","display_name":"Daniel Hein","orcid":"https://orcid.org/0000-0002-8375-1592"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Hein","raw_affiliation_strings":["Siemens AG, Corporate Technology, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG, Corporate Technology, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035246650","display_name":"Steffen Udluft","orcid":"https://orcid.org/0000-0002-5767-2591"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Udluft","raw_affiliation_strings":["Siemens AG, Corporate Technology, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG, Corporate Technology, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002518694","display_name":"Thomas A. Runkler","orcid":"https://orcid.org/0000-0002-5465-198X"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Thomas A. Runkler","raw_affiliation_strings":["Siemens AG, Corporate Technology, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens AG, Corporate Technology, Munich, Germany","institution_ids":["https://openalex.org/I1325886976"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1325886976"],"apc_list":null,"apc_paid":null,"fwci":0.133,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.47863537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"24"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9991000294685364,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.9829999804496765,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.9403173327445984},{"id":"https://openalex.org/keywords/genetic-programming","display_name":"Genetic programming","score":0.84138023853302},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7335370182991028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6796940565109253},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5523852705955505},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5497855544090271},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.47847363352775574},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4519984722137451},{"id":"https://openalex.org/keywords/learning-classifier-system","display_name":"Learning classifier system","score":0.4472348988056183},{"id":"https://openalex.org/keywords/genetic-algorithm","display_name":"Genetic algorithm","score":0.43584030866622925},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42289888858795166},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.41904860734939575},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13714826107025146},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09568396210670471}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9403173327445984},{"id":"https://openalex.org/C110332635","wikidata":"https://www.wikidata.org/wiki/Q629498","display_name":"Genetic programming","level":2,"score":0.84138023853302},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7335370182991028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6796940565109253},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5523852705955505},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5497855544090271},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.47847363352775574},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4519984722137451},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.4472348988056183},{"id":"https://openalex.org/C8880873","wikidata":"https://www.wikidata.org/wiki/Q187787","display_name":"Genetic algorithm","level":2,"score":0.43584030866622925},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42289888858795166},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.41904860734939575},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13714826107025146},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09568396210670471},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3319619.3326755","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3319619.3326755","pdf_url":null,"source":{"id":"https://openalex.org/S4363608771","display_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Genetic and Evolutionary Computation Conference Companion","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W11104910","https://openalex.org/W2760661167","https://openalex.org/W2963672746","https://openalex.org/W3099427826","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2961374456","https://openalex.org/W1966456942","https://openalex.org/W2754028433","https://openalex.org/W3148138296","https://openalex.org/W1882507001","https://openalex.org/W2367922714","https://openalex.org/W2352650970","https://openalex.org/W2534140487","https://openalex.org/W4383501708","https://openalex.org/W2041126907"],"abstract_inverted_index":{"The":[0],"search":[1],"for":[2,15,61,81],"interpretable":[3],"reinforcement":[4,62,82,90,109],"learning":[5,63,83,91,110],"policies":[6,60,118],"is":[7],"of":[8,71,119],"high":[9,120],"academic":[10],"and":[11,32,92,95],"industrial":[12,16],"interest.":[13],"Especially":[14],"systems,":[17],"domain":[18],"experts":[19],"are":[20,30,39,49],"more":[21],"likely":[22],"to":[23,34,41,51],"deploy":[24],"autonomously":[25,96],"learned":[26],"controllers":[27],"if":[28],"they":[29,48],"understandable":[31],"convenient":[33],"evaluate.":[35],"Basic":[36],"algebraic":[37],"equations":[38,99],"supposed":[40],"meet":[42],"these":[43],"requirements,":[44],"as":[45,47],"long":[46],"restricted":[50],"an":[52],"adequate":[53],"complexity.":[54],"In":[55],"our":[56],"recent":[57],"work":[58],"\"Interpretable":[59],"by":[64],"genetic":[65,79,93],"programming\"":[66],"published":[67],"in":[68],"Engineering":[69],"Applications":[70],"Artificial":[72],"Intelligence":[73],"76":[74],"(2018),":[75],"we":[76],"introduced":[77],"the":[78],"programming":[80,94],"(GPRL)":[84],"approach.":[85],"GPRL":[86,114],"uses":[87],"model-based":[88],"batch":[89],"learns":[97],"policy":[98],"from":[100],"preexisting":[101],"default":[102],"state-action":[103],"trajectory":[104],"samples.":[105],"Experiments":[106],"on":[107],"three":[108],"benchmarks":[111],"demonstrate":[112],"that":[113],"can":[115],"produce":[116],"human-interpretable":[117],"control":[121],"performance.":[122]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}