{"id":"https://openalex.org/W4312326293","doi":"https://doi.org/10.1109/iros47612.2022.9981126","title":"How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation","display_name":"How to Spend Your Robot Time: Bridging Kickstarting and Offline Reinforcement Learning for Vision-based Robotic Manipulation","publication_year":2022,"publication_date":"2022-10-23","ids":{"openalex":"https://openalex.org/W4312326293","doi":"https://doi.org/10.1109/iros47612.2022.9981126"},"language":"en","primary_location":{"id":"doi:10.1109/iros47612.2022.9981126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981126","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 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/A5027666200","display_name":"Alex X. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alex X. Lee","raw_affiliation_strings":["DeepMind,London,UK","DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind,London,UK","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079786074","display_name":"Coline Devin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Coline Devin","raw_affiliation_strings":["DeepMind,London,UK","DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind,London,UK","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017985443","display_name":"Jost Tobias Springenberg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jost Tobias Springenberg","raw_affiliation_strings":["DeepMind,London,UK","DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind,London,UK","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102005803","display_name":"Yuxiang Zhou","orcid":"https://orcid.org/0000-0002-6484-745X"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yuxiang Zhou","raw_affiliation_strings":["DeepMind,London,UK","DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind,London,UK","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054636066","display_name":"Thomas Lampe","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Thomas Lampe","raw_affiliation_strings":["DeepMind,London,UK","DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind,London,UK","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007133617","display_name":"Abbas Abdolmaleki","orcid":"https://orcid.org/0000-0001-6692-5856"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Abbas Abdolmaleki","raw_affiliation_strings":["DeepMind,London,UK","DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind,London,UK","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079462322","display_name":"Konstantinos Bousmalis","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Konstantinos Bousmalis","raw_affiliation_strings":["DeepMind,London,UK","DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind,London,UK","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210090411"],"apc_list":null,"apc_paid":null,"fwci":1.5182,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.85470812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2468","last_page":"2475"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11182","display_name":"Auction Theory and Applications","score":0.9746999740600586,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.858952522277832},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.755495011806488},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6617769002914429},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6351221203804016},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.574284017086029},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5117871165275574},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5108160972595215},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5047413110733032},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5036584734916687},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.489094078540802},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38107091188430786},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.0887640118598938}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.858952522277832},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.755495011806488},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6617769002914429},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6351221203804016},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.574284017086029},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5117871165275574},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5108160972595215},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5047413110733032},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5036584734916687},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.489094078540802},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38107091188430786},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0887640118598938},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros47612.2022.9981126","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros47612.2022.9981126","pdf_url":null,"source":{"id":"https://openalex.org/S4363607704","display_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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":40,"referenced_works":["https://openalex.org/W1931877416","https://openalex.org/W2785738552","https://openalex.org/W2799151646","https://openalex.org/W2804930149","https://openalex.org/W2904246096","https://openalex.org/W2904453761","https://openalex.org/W2947150733","https://openalex.org/W2991355586","https://openalex.org/W2995706821","https://openalex.org/W3033324992","https://openalex.org/W3037440645","https://openalex.org/W3093210414","https://openalex.org/W3169514089","https://openalex.org/W3170197122","https://openalex.org/W3170697419","https://openalex.org/W3172360140","https://openalex.org/W3205794883","https://openalex.org/W3207335863","https://openalex.org/W3208796191","https://openalex.org/W4286905708","https://openalex.org/W4287630848","https://openalex.org/W4298174377","https://openalex.org/W4298845604","https://openalex.org/W4298876402","https://openalex.org/W4394657676","https://openalex.org/W6640174482","https://openalex.org/W6683300800","https://openalex.org/W6685726866","https://openalex.org/W6747924173","https://openalex.org/W6757469721","https://openalex.org/W6757592117","https://openalex.org/W6763704811","https://openalex.org/W6771886500","https://openalex.org/W6779265984","https://openalex.org/W6780159193","https://openalex.org/W6780964083","https://openalex.org/W6796589144","https://openalex.org/W6796971187","https://openalex.org/W6797702751","https://openalex.org/W6802395018"],"related_works":["https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W2378211422","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214","https://openalex.org/W2745001401","https://openalex.org/W4321353415"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,10],"(RL)":[2],"has":[3],"been":[4],"shown":[5],"to":[6,31,49,121,141,175],"be":[7],"effective":[8,248],"at":[9,111],"control":[11],"from":[12,69,158,243],"experience.":[13],"However,":[14],"RL":[15,84,147,242],"typically":[16],"requires":[17],"a":[18,54,59,115,126,178,214],"large":[19],"amount":[20],"of":[21,98,119,206,217],"online":[22,51],"interaction":[23,40],"with":[24,134,203],"the":[25,95,109,160,165,184,189,192,226,234],"environment.":[26],"This":[27],"limits":[28],"its":[29],"applicability":[30],"real-world":[32],"settings,":[33],"such":[34,39,106],"as":[35],"in":[36,53,76,222,225],"robotics,":[37],"where":[38],"is":[41,233,246,252],"expensive.":[42],"In":[43],"this":[44,79],"work":[45],"we":[46,62,81,152],"investigate":[47],"ways":[48],"minimize":[50],"interactions":[52],"target":[55,185],"task,":[56],"by":[57,91,105],"reusing":[58],"suboptimal":[60,123],"policy":[61],"might":[63],"have":[64],"access":[65],"to,":[66],"for":[67,168],"example":[68],"training":[70,90,155],"on":[71,108,125,131,156,183],"related":[72],"prior":[73],"tasks,":[74],"or":[75],"simulation.":[77],"To":[78],"end,":[80],"develop":[82],"two":[83,201],"algorithms":[85],"that":[86,154,212,230],"can":[87],"speed":[88],"up":[89],"using":[92,198],"not":[93],"only":[94],"action":[96],"distributions":[97],"teacher":[99,161,190,244],"policies,":[100],"but":[101],"also":[102],"data":[103,157,170,180,237,251],"collected":[104],"policies":[107],"task":[110,186],"hand.":[112],"We":[113,137,172],"conduct":[114],"thorough":[116],"experimental":[117],"study":[118],"how":[120,174],"use":[122],"teachers":[124,202],"challenging":[127],"robotic":[128],"manipulation":[129],"benchmark":[130],"vision-based":[132],"stacking":[133,210],"diverse":[135,215],"objects.":[136],"compare":[138],"our":[139,231],"methods":[140],"offline,":[142],"online,":[143],"offline-to-online,":[144],"and":[145,162,191,195,208,224],"kickstarting":[146],"algorithms.":[148],"By":[149],"doing":[150],"so,":[151],"find":[153],"both":[159,221],"student,":[163],"enables":[164],"best":[166,176,235],"performance":[167],"limited":[169,179],"budgets.":[171],"examine":[173],"allocate":[177],"budget":[181],"-":[182,187],"between":[188],"student":[193],"policy,":[194],"report":[196],"experiments":[197],"varying":[199],"budgets,":[200,238],"different":[204],"degrees":[205],"suboptimality,":[207],"five":[209],"tasks":[211],"require":[213],"set":[216],"behaviors.":[218],"Our":[219],"analysis,":[220],"simulation":[223],"real":[227],"world,":[228],"shows":[229],"approach":[232],"across":[236],"while":[239],"standard":[240],"offline":[241],"rollouts":[245],"surprisingly":[247],"when":[249],"enough":[250],"given.":[253]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}