{"id":"https://openalex.org/W2529601334","doi":"https://doi.org/10.1109/icra.2017.7989384","title":"Path integral guided policy search","display_name":"Path integral guided policy search","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2529601334","doi":"https://doi.org/10.1109/icra.2017.7989384","mag":"2529601334"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2017.7989384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5001178359","display_name":"Yevgen Chebotar","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yevgen Chebotar","raw_affiliation_strings":["Department of Computer Science, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080415080","display_name":"Mrinal Kalakrishnan","orcid":"https://orcid.org/0000-0003-4292-9857"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mrinal Kalakrishnan","raw_affiliation_strings":["X, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069879254","display_name":"Ali Abdullah Yahya","orcid":"https://orcid.org/0000-0002-7805-1225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Yahya","raw_affiliation_strings":["X, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025313946","display_name":"Adrian Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adrian Li","raw_affiliation_strings":["X, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X, Mountain View, CA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029642293","display_name":"Stefan Schaal","orcid":"https://orcid.org/0000-0001-5660-1874"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stefan Schaal","raw_affiliation_strings":["Department of Computer Science, University of Southern California, Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026322200","display_name":"Sergey Levine","orcid":"https://orcid.org/0000-0001-6764-2743"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["Google Brain, Mountain View, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Brain, Mountain View, CA, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":127,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3381","last_page":"3388"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T10581","display_name":"Neural dynamics and brain function","score":0.991599977016449,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7138364315032959},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6853644847869873},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6801506280899048},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5829930901527405},{"id":"https://openalex.org/keywords/global-positioning-system","display_name":"Global Positioning System","score":0.5486626029014587},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5054733753204346},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4373571574687958},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.434447705745697},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3863089084625244},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14270514249801636},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08717206120491028}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7138364315032959},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6853644847869873},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6801506280899048},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5829930901527405},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.5486626029014587},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5054733753204346},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4373571574687958},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.434447705745697},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3863089084625244},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14270514249801636},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08717206120491028},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2017.7989384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Robotics and Automation (ICRA)","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":48,"referenced_works":["https://openalex.org/W314779054","https://openalex.org/W1499669280","https://openalex.org/W1520597402","https://openalex.org/W1771410628","https://openalex.org/W1925816294","https://openalex.org/W1979709633","https://openalex.org/W2001095967","https://openalex.org/W2012587148","https://openalex.org/W2051620263","https://openalex.org/W2060914855","https://openalex.org/W2068923975","https://openalex.org/W2076063813","https://openalex.org/W2098524868","https://openalex.org/W2100235553","https://openalex.org/W2101926813","https://openalex.org/W2104733512","https://openalex.org/W2108579172","https://openalex.org/W2109008048","https://openalex.org/W2110304639","https://openalex.org/W2121103318","https://openalex.org/W2126909264","https://openalex.org/W2136391815","https://openalex.org/W2139053308","https://openalex.org/W2155007355","https://openalex.org/W2161395589","https://openalex.org/W2165776394","https://openalex.org/W2169136412","https://openalex.org/W2474696542","https://openalex.org/W2510228645","https://openalex.org/W2520352517","https://openalex.org/W2591436094","https://openalex.org/W2963864421","https://openalex.org/W2964161785","https://openalex.org/W3005581722","https://openalex.org/W3101102451","https://openalex.org/W4235910938","https://openalex.org/W4297802064","https://openalex.org/W6629881138","https://openalex.org/W6638018090","https://openalex.org/W6640290305","https://openalex.org/W6653548176","https://openalex.org/W6674872077","https://openalex.org/W6675999342","https://openalex.org/W6678367057","https://openalex.org/W6680285999","https://openalex.org/W6682849425","https://openalex.org/W6684921986","https://openalex.org/W6725508859"],"related_works":["https://openalex.org/W3162200841","https://openalex.org/W2586280620","https://openalex.org/W2805505483","https://openalex.org/W2334071950","https://openalex.org/W2384744344","https://openalex.org/W4233932308","https://openalex.org/W1799694159","https://openalex.org/W2393169196","https://openalex.org/W2366610330","https://openalex.org/W4242143973"],"abstract_inverted_index":{"We":[0,28,68,152,174],"present":[1],"a":[2,31,42,51,58,81,119,179,185],"policy":[3,36,62,141,200],"search":[4,37],"method":[5,177],"for":[6,21,47,104,148],"learning":[7],"complex":[8],"feedback":[9],"control":[10,91,170],"policies":[11,46,103,164],"that":[12,63,139,154,165,191,208],"map":[13],"from":[14,171],"high-dimensional":[15,60],"sensory":[16],"inputs":[17],"to":[18,56,100,116,159],"motor":[19],"torques,":[20],"manipulation":[22],"tasks":[23,105],"with":[24,106],"discontinuous":[25,108],"contact":[26,109],"dynamics.":[27],"build":[29],"on":[30,86,118,178,202],"prior":[32,197],"technique":[33],"called":[34],"guided":[35],"(GPS),":[38],"which":[39,97],"iteratively":[40],"optimizes":[41],"set":[43,121],"of":[44,50,80,122,136,216],"local":[45,83,102,199],"specific":[48],"instances":[49,124,138],"task,":[52,187],"and":[53,111,145,184,188],"uses":[54],"these":[55,155,203,217],"train":[57,117],"complex,":[59],"global":[61],"generalizes":[64],"across":[65],"task":[66,123,183],"instances.":[67],"extend":[69],"GPS":[70,115],"in":[71,125],"the":[72,78,134,137,140,176,196,213],"following":[73],"ways:":[74],"(1)":[75],"we":[76,113,189,206],"propose":[77],"use":[79],"model-free":[82],"optimizer":[84,201],"based":[85],"path":[87],"integral":[88],"stochastic":[89],"optimal":[90],"(PI":[92],"<sup":[93],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[94],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[95],"),":[96],"enables":[98],"us":[99,158],"learn":[101,160],"highly":[107],"dynamics;":[110],"(2)":[112],"enable":[114,157],"new":[120],"every":[126],"iteration":[127],"by":[128],"using":[129],"on-policy":[130,209],"sampling:":[131],"this":[132],"increases":[133,212],"diversity":[135],"is":[142,146],"trained":[143],"on,":[144],"crucial":[147],"achieving":[149],"good":[150],"generalization.":[151],"show":[153,207],"contributions":[156],"deep":[161],"neural":[162],"network":[163],"can":[166],"directly":[167],"perform":[168],"torque":[169],"visual":[172],"input.":[173],"validate":[175],"challenging":[180],"door":[181],"opening":[182],"pick-and-place":[186],"demonstrate":[190],"our":[192],"approach":[193],"substantially":[194],"outperforms":[195],"LQR-based":[198],"tasks.":[204],"Furthermore,":[205],"sampling":[210],"significantly":[211],"generalization":[214],"ability":[215],"policies.":[218]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":26},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":24},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":15},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}