{"id":"https://openalex.org/W2221677593","doi":"https://doi.org/10.1109/iros.2015.7354297","title":"Learning compound multi-step controllers under unknown dynamics","display_name":"Learning compound multi-step controllers under unknown dynamics","publication_year":2015,"publication_date":"2015-09-01","ids":{"openalex":"https://openalex.org/W2221677593","doi":"https://doi.org/10.1109/iros.2015.7354297","mag":"2221677593"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2015.7354297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2015.7354297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5028395418","display_name":"Weiqiao Han","orcid":"https://orcid.org/0000-0002-2778-0567"},"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":"Weiqiao Han","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","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, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","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, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":5.7937,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.9752322,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"6435","last_page":"6442"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9998000264167786,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983000159263611,"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/T10879","display_name":"Robotic Locomotion and Control","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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":0.7739970088005066},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7272443771362305},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6704791188240051},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6574580669403076},{"id":"https://openalex.org/keywords/reset","display_name":"Reset (finance)","score":0.6220555901527405},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5926341414451599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5341410040855408},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.48349955677986145},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4151945114135742},{"id":"https://openalex.org/keywords/control-engineering","display_name":"Control engineering","score":0.41152238845825195},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2490537464618683},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.15694266557693481},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.07765984535217285}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7739970088005066},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7272443771362305},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6704791188240051},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6574580669403076},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.6220555901527405},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5926341414451599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5341410040855408},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.48349955677986145},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4151945114135742},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.41152238845825195},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2490537464618683},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15694266557693481},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.07765984535217285},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2015.7354297","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2015.7354297","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W195033972","https://openalex.org/W1520597402","https://openalex.org/W1963873191","https://openalex.org/W2001095967","https://openalex.org/W2012587148","https://openalex.org/W2042882799","https://openalex.org/W2051620263","https://openalex.org/W2060914855","https://openalex.org/W2063346060","https://openalex.org/W2088038240","https://openalex.org/W2104733512","https://openalex.org/W2108535023","https://openalex.org/W2109008048","https://openalex.org/W2121103318","https://openalex.org/W2125612430","https://openalex.org/W2126909264","https://openalex.org/W2139053308","https://openalex.org/W2155007355","https://openalex.org/W2156377376","https://openalex.org/W2161395589","https://openalex.org/W2296319761","https://openalex.org/W2400535959","https://openalex.org/W2591436094","https://openalex.org/W2964161785","https://openalex.org/W4205513846","https://openalex.org/W4250589301","https://openalex.org/W6607786297","https://openalex.org/W6675999342","https://openalex.org/W6676557315","https://openalex.org/W6678367057","https://openalex.org/W6678872352","https://openalex.org/W6682849425","https://openalex.org/W6683180588","https://openalex.org/W6712948466","https://openalex.org/W7073827480"],"related_works":["https://openalex.org/W350273603","https://openalex.org/W2393495588","https://openalex.org/W96259911","https://openalex.org/W2168225754","https://openalex.org/W4385608460","https://openalex.org/W2370772865","https://openalex.org/W1528611913","https://openalex.org/W2000034628","https://openalex.org/W2387487224","https://openalex.org/W2000675896"],"abstract_inverted_index":{"Applications":[0],"of":[1,24,66,103,140,171],"reinforcement":[2,16,69],"learning":[3,17,118],"for":[4,63,227],"robotic":[5],"manipulation":[6],"often":[7,19],"assume":[8],"an":[9,61],"episodic":[10],"setting.":[11],"However,":[12],"controllers":[13,32,46,67,82,92,130,146,198,226],"trained":[14],"with":[15,68,148,216,231],"are":[18],"situated":[20],"in":[21,36,83,115,182,234],"the":[22,50,76,84,96,109,197,201],"context":[23],"a":[25,40,116,123,149,164,177,183,228],"more":[26],"complex":[27,165,192],"compound":[28,186],"task,":[29],"where":[30],"multiple":[31],"might":[33],"be":[34,214],"invoked":[35],"sequence":[37],"to":[38,180,220],"accomplish":[39],"higher-level":[41],"goal.":[42],"Furthermore,":[43],"training":[44,64,90,145,156],"such":[45],"typically":[47,56],"requires":[48,72,175,188],"resetting":[49],"environment":[51],"between":[52,98],"episodes,":[53],"which":[54],"is":[55,106],"handled":[57],"manually.":[58],"We":[59,120,158],"describe":[60],"approach":[62],"chains":[65],"learning.":[70],"This":[71,185],"taking":[73],"into":[74],"account":[75],"state":[77,102],"distributions":[78],"induced":[79],"by":[80,108],"preceding":[81],"chain,":[85],"as":[86,88],"well":[87],"automatically":[89,221],"reset":[91,95,151],"that":[93,111,122,127,144,169,210],"can":[94,136,199,213],"task":[97,168,187,203,230],"episodes.":[99],"The":[100],"initial":[101],"each":[104],"controller":[105,110,152],"determined":[107],"precedes":[112],"it,":[113],"resulting":[114],"non-stationary":[117,141],"problem.":[119],"demonstrate":[121,160],"recently":[124],"developed":[125],"method":[126,162,212],"optimizes":[128],"linear-Gaussian":[129],"under":[131],"learned":[132],"local":[133],"linear":[134],"models":[135],"tackle":[137],"this":[138,161,211],"sort":[139],"problem,":[142],"and":[143,174,190,205],"concurrently":[147],"corresponding":[150],"only":[153],"minimally":[154],"increases":[155],"time.":[157],"also":[159],"on":[163],"tool":[166],"use":[167],"consists":[170],"seven":[172],"stages":[173],"using":[176],"toy":[178],"wrench":[179],"screw":[181],"bolt.":[184],"grasping":[189,229],"handling":[191],"contact":[193],"dynamics.":[194],"After":[195],"training,":[196],"execute":[200],"entire":[202],"quickly":[204],"efficiently.":[206],"Finally,":[207],"we":[208],"show":[209],"combined":[215],"guided":[217],"policy":[218],"search":[219],"train":[222],"nonlinear":[223],"neural":[224],"network":[225],"considerable":[232],"variation":[233],"target":[235],"position.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":7},{"year":2020,"cited_by_count":6},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}