{"id":"https://openalex.org/W2897023949","doi":"https://doi.org/10.1109/ijcnn.2018.8489088","title":"A Reinforcement Learning Method for Continuous Domains Using Artificial Hydrocarbon Networks","display_name":"A Reinforcement Learning Method for Continuous Domains Using Artificial Hydrocarbon Networks","publication_year":2018,"publication_date":"2018-07-01","ids":{"openalex":"https://openalex.org/W2897023949","doi":"https://doi.org/10.1109/ijcnn.2018.8489088","mag":"2897023949"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2018.8489088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","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/A5016698194","display_name":"Hiram P\u00f6nce","orcid":"https://orcid.org/0000-0002-6559-7501"},"institutions":[{"id":"https://openalex.org/I86613570","display_name":"Universidad Panamericana","ror":"https://ror.org/01n1q0h77","country_code":"MX","type":"education","lineage":["https://openalex.org/I86613570"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Hiram Ponce","raw_affiliation_strings":["Universidad Panamericana, Facultad de Ingenier\u00eda. Augusto Rodin 498, M\u00e9xico, Ciudad de M\u00e9xico, M\u00e9xico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Panamericana, Facultad de Ingenier\u00eda. Augusto Rodin 498, M\u00e9xico, Ciudad de M\u00e9xico, M\u00e9xico","institution_ids":["https://openalex.org/I86613570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062771271","display_name":"Guillermo Gonz\u00e1lez-Mora","orcid":null},"institutions":[{"id":"https://openalex.org/I86613570","display_name":"Universidad Panamericana","ror":"https://ror.org/01n1q0h77","country_code":"MX","type":"education","lineage":["https://openalex.org/I86613570"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Guillermo Gonzalez-Mora","raw_affiliation_strings":["Universidad Panamericana, Facultad de Ingenier\u00eda. Augusto Rodin 498, M\u00e9xico, Ciudad de M\u00e9xico, M\u00e9xico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Panamericana, Facultad de Ingenier\u00eda. Augusto Rodin 498, M\u00e9xico, Ciudad de M\u00e9xico, M\u00e9xico","institution_ids":["https://openalex.org/I86613570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038538096","display_name":"Lourdes Mart\u00ednez-Villase\u00f1or","orcid":"https://orcid.org/0000-0002-9038-7821"},"institutions":[{"id":"https://openalex.org/I86613570","display_name":"Universidad Panamericana","ror":"https://ror.org/01n1q0h77","country_code":"MX","type":"education","lineage":["https://openalex.org/I86613570"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"Lourdes Martinez-Villasenor","raw_affiliation_strings":["Universidad Panamericana, Facultad de Ingenier\u00eda. Augusto Rodin 498, M\u00e9xico, Ciudad de M\u00e9xico, M\u00e9xico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Panamericana, Facultad de Ingenier\u00eda. Augusto Rodin 498, M\u00e9xico, Ciudad de M\u00e9xico, M\u00e9xico","institution_ids":["https://openalex.org/I86613570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5069,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74580277,"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","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/T10462","display_name":"Reinforcement Learning in Robotics","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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9922000169754028,"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"}},{"id":"https://openalex.org/T10409","display_name":"Fuel Cells and Related Materials","score":0.9908000230789185,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8717048168182373},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6302580833435059},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5855525135993958},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5481113791465759},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4881945252418518},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.47064894437789917},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.46921077370643616},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.4480677545070648},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4424035847187042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.220132976770401},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15431278944015503},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.14729145169258118},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1178111732006073}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8717048168182373},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6302580833435059},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5855525135993958},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5481113791465759},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4881945252418518},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.47064894437789917},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.46921077370643616},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.4480677545070648},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4424035847187042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.220132976770401},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15431278944015503},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.14729145169258118},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1178111732006073},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn.2018.8489088","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2018.8489088","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Joint Conference on Neural Networks (IJCNN)","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":25,"referenced_works":["https://openalex.org/W1191599655","https://openalex.org/W1965387791","https://openalex.org/W1987951573","https://openalex.org/W2012587148","https://openalex.org/W2105442158","https://openalex.org/W2109102709","https://openalex.org/W2121517924","https://openalex.org/W2140135625","https://openalex.org/W2173248099","https://openalex.org/W2290354866","https://openalex.org/W2312609093","https://openalex.org/W2519881245","https://openalex.org/W2540548357","https://openalex.org/W2740042657","https://openalex.org/W2768794893","https://openalex.org/W2950471160","https://openalex.org/W4205513846","https://openalex.org/W4214717370","https://openalex.org/W4241194895","https://openalex.org/W6627932998","https://openalex.org/W6675894441","https://openalex.org/W6680657880","https://openalex.org/W6696324988","https://openalex.org/W6741699995","https://openalex.org/W6745600969"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W2031695474","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2586732548","https://openalex.org/W3049728571"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,41,54],"in":[2,11,15,25,45,122,126,131,140,143],"continuous":[3,56,79,123],"states":[4,57],"and":[5,58,89,135],"actions":[6,59],"has":[7],"been":[8],"limitedly":[9],"studied":[10],"ocassions":[12],"given":[13],"difficulties":[14],"the":[16,19,75,78,82,97,100,107],"determination":[17],"of":[18,23,77,99],"transition":[20],"function,":[21],"lack":[22],"performance":[24],"continuous-to-discrete":[26],"relaxation":[27],"problems,":[28,34],"among":[29],"others.":[30],"For":[31],"instance,":[32],"real-world":[33],"e.g.":[35],"robotics,":[36],"require":[37],"these":[38],"methods":[39],"for":[40,52],"complex":[42],"tasks.":[43],"Thus,":[44],"this":[46],"paper,":[47],"we":[48],"propose":[49],"a":[50,61,148],"method":[51,72],"reinforcement":[53],"with":[55,65,81],"using":[60],"model-based":[62,120],"approach":[63],"learned":[64],"artificial":[66,114],"hydrocarbon":[67,115],"networks":[68,116],"(AHN).":[69],"The":[70],"proposed":[71],"considers":[73],"modeling":[74],"dynamics":[76,102],"task":[80,111],"supervised":[83],"AHN":[84],"method.":[85],"Initial":[86],"random":[87],"rollouts":[88],"posterior":[90],"data":[91],"collection":[92],"from":[93,159],"policy":[94,137],"evaluation":[95],"improve":[96],"training":[98],"AHN-based":[101],"model.":[103],"Preliminary":[104],"results":[105,161],"over":[106,147],"well-known":[108],"mountain":[109],"car":[110],"showed":[112],"that":[113],"can":[117],"contribute":[118],"to":[119],"approaches":[121],"RL":[124],"problems":[125],"both":[127],"estimation":[128],"efficiency":[129],"(0.0012":[130],"root":[132],"mean":[133],"squared-error)":[134],"sub-optimal":[136],"convergence":[138],"(reached":[139],"357":[141],"steps),":[142],"just":[144],"5":[145],"trials":[146],"parameter":[149],"space":[150],"\u03b8":[151],"\u2208":[152],"R":[153],"<sup":[154],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[155],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">86</sup>":[156],".":[157],"Data":[158],"experimental":[160],"are":[162],"available":[163],"at:":[164],"http://sites.google.com/up.edu.mx/reinforcement-learning/http://sites.google.com/up.edu.mx/reinforcement-learning/.":[165]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}