{"id":"https://openalex.org/W2528734395","doi":"https://doi.org/10.1109/icra.2017.7989383","title":"Reset-free guided policy search: Efficient deep reinforcement learning with stochastic initial states","display_name":"Reset-free guided policy search: Efficient deep reinforcement learning with stochastic initial states","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2528734395","doi":"https://doi.org/10.1109/icra.2017.7989383","mag":"2528734395"},"language":"en","primary_location":{"id":"doi:10.1109/icra.2017.7989383","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989383","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":"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/A5102831923","display_name":"William Montgomery","orcid":"https://orcid.org/0000-0003-4991-3655"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"William Montgomery","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Washington, Seattle, WA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Washington, Seattle, WA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102336100","display_name":"Anurag Ajay","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anurag Ajay","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chelsea Finn","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049349154","display_name":"Pieter Abbeel","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pieter Abbeel","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]},{"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/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sergey Levine","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California Berkeley, Berkeley, CA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102831923"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":3.3153,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.93645124,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"3373","last_page":"3380"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.9976999759674072,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9843000173568726,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8838105201721191},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7349451780319214},{"id":"https://openalex.org/keywords/reset","display_name":"Reset (finance)","score":0.7037662267684937},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7031616568565369},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6381537914276123},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5661394000053406},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.563152015209198},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5483851432800293},{"id":"https://openalex.org/keywords/global-positioning-system","display_name":"Global Positioning System","score":0.5131509900093079},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.49619513750076294},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.43654462695121765},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4315029978752136}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8838105201721191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7349451780319214},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.7037662267684937},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7031616568565369},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6381537914276123},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5661394000053406},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.563152015209198},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5483851432800293},{"id":"https://openalex.org/C60229501","wikidata":"https://www.wikidata.org/wiki/Q18822","display_name":"Global Positioning System","level":2,"score":0.5131509900093079},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.49619513750076294},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43654462695121765},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4315029978752136},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra.2017.7989383","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra.2017.7989383","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":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310094","display_name":"University of Washington","ror":"https://ror.org/00cvxb145"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1499669280","https://openalex.org/W1515851193","https://openalex.org/W1533535072","https://openalex.org/W1771410628","https://openalex.org/W1977655452","https://openalex.org/W2012587148","https://openalex.org/W2016384870","https://openalex.org/W2100235553","https://openalex.org/W2109008048","https://openalex.org/W2121103318","https://openalex.org/W2123967136","https://openalex.org/W2155007355","https://openalex.org/W2158782408","https://openalex.org/W2161395589","https://openalex.org/W2165150801","https://openalex.org/W2167856595","https://openalex.org/W2169209873","https://openalex.org/W2342662072","https://openalex.org/W2473408367","https://openalex.org/W2952063594","https://openalex.org/W2963630259","https://openalex.org/W2963641140","https://openalex.org/W2963864421","https://openalex.org/W2964161785","https://openalex.org/W4250589301","https://openalex.org/W4297802064","https://openalex.org/W4302570325","https://openalex.org/W6629881138","https://openalex.org/W6631863446","https://openalex.org/W6638018090","https://openalex.org/W6653548176","https://openalex.org/W6678157427","https://openalex.org/W6678367057","https://openalex.org/W6682849425","https://openalex.org/W6684205842","https://openalex.org/W6684921986","https://openalex.org/W6685331716","https://openalex.org/W6704571135","https://openalex.org/W6720923776","https://openalex.org/W6725508859"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2166117066","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915"],"abstract_inverted_index":{"Autonomous":[0],"learning":[1,21,60,79,96,100],"of":[2,46,119],"robotic":[3,19],"skills":[4],"can":[5,63,134,164,180,198],"allow":[6],"general-purpose":[7,65],"robots":[8],"to":[9,26,110,122,141,154],"learn":[10,181,199],"wide":[11],"behavioral":[12],"repertoires":[13],"without":[14],"extensive":[15],"manual":[16],"engineering.":[17],"However,":[18],"skill":[20],"must":[22,126],"typically":[23],"make":[24],"trade-offs":[25],"enable":[27],"practical":[28],"real-world":[29,190],"learning,":[30],"such":[31],"as":[32,175],"requiring":[33],"manually":[34],"designed":[35],"policy":[36,88,156],"or":[37,50],"value":[38],"function":[39],"representations,":[40],"initialization":[41],"from":[42,101,184],"human":[43,71,106],"demonstrations,":[44],"instrumentation":[45],"the":[47,86,94,124,171],"training":[48,53],"environment,":[49],"extremely":[51],"long":[52],"times.":[54],"We":[55,83,150,187],"propose":[56],"a":[57,102,116],"new":[58],"reinforcement":[59,95],"algorithm":[61],"that":[62,162,193,195],"train":[64,165],"neural":[66,167],"network":[67,168],"policies":[68,169,182,201],"with":[69,170,202],"minimal":[70],"engineering,":[72],"while":[73],"still":[74],"allowing":[75,139],"for":[76],"fast,":[77],"efficient":[78],"in":[80,159],"stochastic":[81],"environments.":[82],"build":[84],"on":[85],"guided":[87],"search":[89,157],"(GPS)":[90],"algorithm,":[91],"which":[92,114,123],"transforms":[93],"problem":[97],"into":[98],"supervised":[99],"computational":[103],"teacher":[104],"(without":[105],"demonstrations).":[107],"In":[108],"contrast":[109],"prior":[111,176],"GPS":[112,177],"methods,":[113,178],"require":[115],"consistent":[117],"set":[118],"initial":[120,137,207],"states":[121],"system":[125],"be":[127,142],"reset":[128],"after":[129],"each":[130],"episode,":[131],"our":[132,152,196],"approach":[133],"handle":[135],"random":[136,206],"states,":[138],"it":[140,163],"used":[143],"even":[144],"when":[145],"deterministic":[146],"resets":[147],"are":[148],"impossible.":[149],"compare":[151],"method":[153,197],"existing":[155],"algorithms":[158],"simulation,":[160],"showing":[161],"high-dimensional":[166],"same":[172],"sample":[173],"efficiency":[174],"and":[179,205],"directly":[183],"image":[185],"pixels.":[186],"also":[188],"present":[189],"robot":[191],"results":[192],"show":[194],"manipulation":[200],"visual":[203],"features":[204],"states.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}