{"id":"https://openalex.org/W3005581722","doi":"https://doi.org/10.5555/1756006.1953033","title":"A Generalized Path Integral Control Approach to Reinforcement Learning","display_name":"A Generalized Path Integral Control Approach to Reinforcement Learning","publication_year":2010,"publication_date":"2010-12-01","ids":{"openalex":"https://openalex.org/W3005581722","doi":"https://doi.org/10.5555/1756006.1953033","mag":"3005581722"},"language":"en","primary_location":{"id":"mag:3005581722","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/1756006.1953033","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research","raw_type":null},"type":"article","indexed_in":[],"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/A5081942390","display_name":"TheodorouEvangelos","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"TheodorouEvangelos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024800069","display_name":"BuchliJonas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"BuchliJonas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051412797","display_name":"SchaalStefan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"SchaalStefan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":28.8835,"has_fulltext":false,"cited_by_count":286,"citation_normalized_percentile":{"value":0.99679971,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.8960000276565552,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T14083","display_name":"Extremum Seeking Control Systems","score":0.8960000276565552,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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":0.6455828547477722},{"id":"https://openalex.org/keywords/path-integral-formulation","display_name":"Path integral formulation","score":0.5915130972862244},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5137346982955933},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.4852164089679718},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.472768098115921},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4375470280647278},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35089802742004395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3490946888923645},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3200792968273163},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12326177954673767},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09946605563163757}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6455828547477722},{"id":"https://openalex.org/C154018700","wikidata":"https://www.wikidata.org/wiki/Q898323","display_name":"Path integral formulation","level":3,"score":0.5915130972862244},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5137346982955933},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4852164089679718},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.472768098115921},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4375470280647278},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35089802742004395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3490946888923645},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3200792968273163},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12326177954673767},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09946605563163757},{"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3005581722","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/1756006.1953033","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Journal of Machine Learning Research","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1925816294","https://openalex.org/W1624779897","https://openalex.org/W2917322258","https://openalex.org/W3148138296","https://openalex.org/W2557003457","https://openalex.org/W2136617285","https://openalex.org/W2909152095","https://openalex.org/W2164056559","https://openalex.org/W2113921460","https://openalex.org/W1603605173","https://openalex.org/W2042882799","https://openalex.org/W2131074440","https://openalex.org/W2887039782","https://openalex.org/W2389511778","https://openalex.org/W1982113044","https://openalex.org/W2775408020","https://openalex.org/W3097722660","https://openalex.org/W1966805688","https://openalex.org/W3103145727","https://openalex.org/W2121296643"],"abstract_inverted_index":{"With":[0],"the":[1],"goal":[2],"to":[3],"generate":[4],"more":[5],"scalable":[6],"algorithms":[7],"with":[8],"higher":[9],"efficiency":[10],"and":[11],"fewer":[12],"open":[13],"parameters,":[14],"reinforcement":[15],"learning":[16],"(RL)":[17],"has":[18],"recently":[19],"moved":[20],"towards":[21],"combining":[22],"classical":[23],"techniques":[24],"from":[25],"optim...":[26]},"counts_by_year":[{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":15},{"year":2023,"cited_by_count":23},{"year":2022,"cited_by_count":27},{"year":2021,"cited_by_count":21},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":19},{"year":2018,"cited_by_count":25},{"year":2017,"cited_by_count":24},{"year":2016,"cited_by_count":16},{"year":2015,"cited_by_count":23},{"year":2014,"cited_by_count":21},{"year":2013,"cited_by_count":15},{"year":2012,"cited_by_count":19}],"updated_date":"2025-10-10T17:16:08.811792","created_date":"2025-10-10T00:00:00"}