{"id":"https://openalex.org/W3146607090","doi":"https://doi.org/10.1109/icra48506.2021.9561232","title":"LASER: Learning a Latent Action Space for Efficient Reinforcement Learning","display_name":"LASER: Learning a Latent Action Space for Efficient Reinforcement Learning","publication_year":2021,"publication_date":"2021-05-30","ids":{"openalex":"https://openalex.org/W3146607090","doi":"https://doi.org/10.1109/icra48506.2021.9561232","mag":"3146607090"},"language":"en","primary_location":{"id":"doi:10.1109/icra48506.2021.9561232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.15793","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013859228","display_name":"Arthur Allshire","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Arthur Allshire","raw_affiliation_strings":["Vector Institute, University of Toronto","University of Toronto;Vector Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vector Institute, University of Toronto","institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4210127509"]},{"raw_affiliation_string":"University of Toronto;Vector Institute","institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4210127509"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065655761","display_name":"Roberto Mart\u00edn-Mart\u00edn","orcid":"https://orcid.org/0000-0002-9586-2759"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roberto Martin-Martin","raw_affiliation_strings":["Stanford University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101429135","display_name":"Charles C. Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Lin","raw_affiliation_strings":["Stanford University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016926782","display_name":"Shawn Manuel","orcid":"https://orcid.org/0009-0003-6462-6512"},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shawn Manuel","raw_affiliation_strings":["Stanford University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042646536","display_name":"Silvio Savarese","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Silvio Savarese","raw_affiliation_strings":["Stanford University","Stanford University ()"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"Stanford University ()","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061193324","display_name":"Animesh Garg","orcid":"https://orcid.org/0000-0003-0482-4296"},"institutions":[{"id":"https://openalex.org/I1304085615","display_name":"Nvidia (United Kingdom)","ror":"https://ror.org/02kr42612","country_code":"GB","type":"company","lineage":["https://openalex.org/I1304085615","https://openalex.org/I4210127875"]},{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]},{"id":"https://openalex.org/I4210127509","display_name":"Vector Institute","ror":"https://ror.org/03kqdja62","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210127509"]}],"countries":["CA","GB"],"is_corresponding":false,"raw_author_name":"Animesh Garg","raw_affiliation_strings":["Nvidia","Vector Institute, University of Toronto","University of Toronto;Vector Institute"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia","institution_ids":["https://openalex.org/I1304085615"]},{"raw_affiliation_string":"Vector Institute, University of Toronto","institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4210127509"]},{"raw_affiliation_string":"University of Toronto;Vector Institute","institution_ids":["https://openalex.org/I185261750","https://openalex.org/I4210127509"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7318,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.71561026,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6650","last_page":"6656"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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":0.9965000152587891,"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/T10260","display_name":"Software Engineering Research","score":0.9045000076293945,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.77142333984375},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.658076822757721},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.628841757774353},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6190057992935181},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5903742909431458},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5217448472976685},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42727676033973694},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0746714174747467}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.77142333984375},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.658076822757721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.628841757774353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6190057992935181},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5903742909431458},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5217448472976685},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42727676033973694},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0746714174747467},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/icra48506.2021.9561232","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48506.2021.9561232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.15793","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.15793","pdf_url":"https://arxiv.org/pdf/2103.15793","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:3146607090","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2103.15793.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.15793","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.15793","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.15793","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.15793","pdf_url":"https://arxiv.org/pdf/2103.15793","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5099999904632568,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3146607090.pdf","grobid_xml":"https://content.openalex.org/works/W3146607090.grobid-xml"},"referenced_works_count":53,"referenced_works":["https://openalex.org/W59183349","https://openalex.org/W1536990779","https://openalex.org/W1556824961","https://openalex.org/W1959608418","https://openalex.org/W1978023077","https://openalex.org/W2017239762","https://openalex.org/W2105660272","https://openalex.org/W2109910161","https://openalex.org/W2110304639","https://openalex.org/W2112474089","https://openalex.org/W2121863487","https://openalex.org/W2133932631","https://openalex.org/W2151992157","https://openalex.org/W2181347294","https://openalex.org/W2461871279","https://openalex.org/W2604763608","https://openalex.org/W2736730521","https://openalex.org/W2783034017","https://openalex.org/W2904246096","https://openalex.org/W2919658942","https://openalex.org/W2938321354","https://openalex.org/W2944912181","https://openalex.org/W2963262099","https://openalex.org/W2964158321","https://openalex.org/W2964161785","https://openalex.org/W2964227312","https://openalex.org/W2996698477","https://openalex.org/W3003524200","https://openalex.org/W3003629310","https://openalex.org/W3008165446","https://openalex.org/W3022253254","https://openalex.org/W3032223429","https://openalex.org/W3037007134","https://openalex.org/W3044718039","https://openalex.org/W3088304681","https://openalex.org/W3090359064","https://openalex.org/W4243385754","https://openalex.org/W4285719527","https://openalex.org/W6640963894","https://openalex.org/W6682849425","https://openalex.org/W6685777803","https://openalex.org/W6703271639","https://openalex.org/W6731982132","https://openalex.org/W6736057607","https://openalex.org/W6744627333","https://openalex.org/W6757592117","https://openalex.org/W6759315145","https://openalex.org/W6765879051","https://openalex.org/W6766767334","https://openalex.org/W6767796685","https://openalex.org/W6769673253","https://openalex.org/W6777058929","https://openalex.org/W6782766965"],"related_works":["https://openalex.org/W3105186190","https://openalex.org/W298069310","https://openalex.org/W3080495593","https://openalex.org/W2911820093","https://openalex.org/W2617816519","https://openalex.org/W2950197980","https://openalex.org/W3130336107","https://openalex.org/W2964158321","https://openalex.org/W3005639539","https://openalex.org/W3206746211","https://openalex.org/W2789102901","https://openalex.org/W3035041226","https://openalex.org/W3092221880","https://openalex.org/W2732054432","https://openalex.org/W1523133203","https://openalex.org/W3175737412","https://openalex.org/W2989941899","https://openalex.org/W2184441712","https://openalex.org/W2294805292","https://openalex.org/W2158150115"],"abstract_inverted_index":{"The":[0],"process":[1],"of":[2,37,64,69,183,206,219],"learning":[3,27,92,100,103,185],"a":[4,23,62,78,132,138,146,155],"manipulation":[5,114],"task":[6,24,40,53,115,212],"depends":[7],"strongly":[8],"on":[9,46,172],"the":[10,18,38,47,52,65,70,91,105,135,181,187,199,207,211,220],"action":[11,20,50,67,83,98,107,140,158,162,190,201,208,222],"space":[12,68,99,159,166,202,209,223],"used":[13],"for":[14,85],"exploration:":[15],"posed":[16],"in":[17,61,104,177,186],"incorrect":[19],"space,":[21,213],"solving":[22],"with":[25,59,217],"reinforcement":[26,87],"can":[28,55],"be":[29,56],"drastically":[30],"inefficient.":[31],"Additionally,":[32],"similar":[33,113],"tasks":[34,176],"or":[35,122],"instances":[36],"same":[39],"family":[41,54],"impose":[42],"latent":[43,82,139,157,165,189],"manifold":[44,63],"constraints":[45],"most":[48],"effective":[49],"space:":[51],"best":[57],"solved":[58],"actions":[60,153],"entire":[66],"robot.":[71],"Combining":[72],"these":[73,130],"insights":[74],"we":[75,215],"present":[76],"LASER,":[77],"method":[79],"to":[80,137,150,198,210],"learn":[81],"spaces":[84],"efficient":[86],"learning.":[88],"LASER":[89,142,171],"factorizes":[90],"problem":[93],"into":[94,154],"two":[95,173],"sub-problems,":[96],"namely":[97],"and":[101,127,164,179],"policy":[102,125,184],"new":[106],"space.":[108,141,191],"It":[109],"leverages":[110],"data":[111],"from":[112,118,129,134,203],"instances,":[116],"either":[117],"an":[119],"offline":[120],"expert":[121],"online":[123],"during":[124],"learning,":[126],"learns":[128],"trajectories":[131],"mapping":[133],"original":[136,200],"is":[143],"trained":[144],"as":[145,214],"variational":[147],"encoder-decoder":[148],"model":[149],"map":[151],"raw":[152],"disentangled":[156],"while":[160],"maintaining":[161],"reconstruction":[163],"dynamic":[167],"consistency.":[168],"We":[169,192],"evaluate":[170],"contact-rich":[174],"robotic":[175],"simulation,":[178],"analyze":[180],"benefit":[182],"generated":[188],"show":[193],"improved":[194],"sample":[195],"efficiency":[196],"compared":[197],"better":[204],"alignment":[205],"observe":[216],"visualizations":[218],"learned":[221],"manifold.":[224],"Additional":[225],"details:":[226],"pair.toronto.edu/laser":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}