{"id":"https://openalex.org/W3131249706","doi":"https://doi.org/10.1109/iros45743.2020.9341629","title":"Reinforcement Learning in Latent Action Sequence Space","display_name":"Reinforcement Learning in Latent Action Sequence Space","publication_year":2020,"publication_date":"2020-10-24","ids":{"openalex":"https://openalex.org/W3131249706","doi":"https://doi.org/10.1109/iros45743.2020.9341629","mag":"3131249706"},"language":"en","primary_location":{"id":"doi:10.1109/iros45743.2020.9341629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5102020002","display_name":"Hee\u2010Cheol Kim","orcid":"https://orcid.org/0000-0002-5399-7647"},"institutions":[{"id":"https://openalex.org/I4210105785","display_name":"Intelligent Systems Research (United States)","ror":"https://ror.org/01reevc91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105785"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP","US"],"is_corresponding":true,"raw_author_name":"Heecheol Kim","raw_affiliation_strings":["Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo","institution_ids":["https://openalex.org/I4210105785","https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037036505","display_name":"Masanori Yamada","orcid":"https://orcid.org/0000-0002-6493-8554"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masanori Yamada","raw_affiliation_strings":["NTT Secure Platform Laboratories"],"affiliations":[{"raw_affiliation_string":"NTT Secure Platform Laboratories","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090881110","display_name":"Kosuke Miyoshi","orcid":"https://orcid.org/0000-0002-8237-1395"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kosuke Miyoshi","raw_affiliation_strings":["narrative nights inc"],"affiliations":[{"raw_affiliation_string":"narrative nights inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034538103","display_name":"Tomoharu Iwata","orcid":"https://orcid.org/0000-0003-4425-1971"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomoharu Iwata","raw_affiliation_strings":["NTT Communication Science Laboratories"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075841450","display_name":"Hiroshi Yamakawa","orcid":"https://orcid.org/0000-0002-6981-0349"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hiroshi Yamakawa","raw_affiliation_strings":["Dwango Artificial Intelligence Laboratory"],"affiliations":[{"raw_affiliation_string":"Dwango Artificial Intelligence Laboratory","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5102020002"],"corresponding_institution_ids":["https://openalex.org/I4210105785","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.2651,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.65628383,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"518","issue":null,"first_page":"5497","last_page":"5503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9962999820709229,"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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9944999814033508,"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":0.8955838680267334},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.736962080001831},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7023743391036987},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6926561594009399},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6913178563117981},{"id":"https://openalex.org/keywords/macro","display_name":"Macro","score":0.6898128986358643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6358175277709961},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5778011083602905},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4442391097545624},{"id":"https://openalex.org/keywords/sequence-learning","display_name":"Sequence learning","score":0.442468523979187},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4177822172641754}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8955838680267334},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.736962080001831},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7023743391036987},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6926561594009399},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6913178563117981},{"id":"https://openalex.org/C166955791","wikidata":"https://www.wikidata.org/wiki/Q629579","display_name":"Macro","level":2,"score":0.6898128986358643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6358175277709961},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5778011083602905},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4442391097545624},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.442468523979187},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4177822172641754},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros45743.2020.9341629","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros45743.2020.9341629","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.6299999952316284,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1585861384","https://openalex.org/W1684361744","https://openalex.org/W1959608418","https://openalex.org/W2109910161","https://openalex.org/W2145339207","https://openalex.org/W2155007355","https://openalex.org/W2163605009","https://openalex.org/W2167224731","https://openalex.org/W2428834750","https://openalex.org/W2442341664","https://openalex.org/W2575705757","https://openalex.org/W2591674338","https://openalex.org/W2592915494","https://openalex.org/W2605102581","https://openalex.org/W2736601468","https://openalex.org/W2782961382","https://openalex.org/W2807692250","https://openalex.org/W2907537824","https://openalex.org/W2908019232","https://openalex.org/W2950462959","https://openalex.org/W2963616477","https://openalex.org/W2963664914","https://openalex.org/W2963669336","https://openalex.org/W2963830168","https://openalex.org/W2964043796","https://openalex.org/W2964161785","https://openalex.org/W2964227312","https://openalex.org/W4211008118","https://openalex.org/W4289146965","https://openalex.org/W4295184135","https://openalex.org/W4394657744","https://openalex.org/W6640963894","https://openalex.org/W6682849425","https://openalex.org/W6684191040","https://openalex.org/W6684338915","https://openalex.org/W6691861496","https://openalex.org/W6692846177","https://openalex.org/W6718233198","https://openalex.org/W6733732937","https://openalex.org/W6734451663","https://openalex.org/W6736298280","https://openalex.org/W6741002519","https://openalex.org/W6748034048","https://openalex.org/W6757380569","https://openalex.org/W6766234440","https://openalex.org/W6864243915"],"related_works":["https://openalex.org/W2030816003","https://openalex.org/W4239992647","https://openalex.org/W2150013480","https://openalex.org/W1554458299","https://openalex.org/W81423522","https://openalex.org/W1509860481","https://openalex.org/W2488264085","https://openalex.org/W2076325756","https://openalex.org/W4386206750","https://openalex.org/W4238700786"],"abstract_inverted_index":{"One":[0],"problem":[1],"in":[2,89,129,146],"real-world":[3],"applications":[4],"of":[5,12,22,30,43,66,87,155,165,187],"reinforcement":[6,76,80,177],"learning":[7,77,81,145,178],"is":[8,134],"the":[9,13,20,28,67,120,130,147,153,156,172],"high":[10],"dimensionality":[11,29,154],"action":[14,31,74,96,157,166],"search":[15,33,98,159],"spaces,":[16,34],"which":[17,40,133],"comes":[18],"from":[19],"combination":[21],"actions":[23,36,45,58,62,88,118,140],"over":[24,137],"time.":[25],"To":[26],"reduce":[27,152],"sequence":[32,75,97,158],"macro":[35,57,61,117,139],"have":[37],"been":[38],"studied,":[39],"are":[41,106],"sequences":[42,86],"primitive":[44,69],"to":[46,55,63],"solve":[47],"tasks.":[48],"However,":[49],"previous":[50],"studies":[51],"relied":[52],"on":[53,180],"humans":[54],"define":[56],"or":[59],"assumed":[60],"be":[64],"repetitions":[65],"same":[68],"actions.":[70],"We":[71,168],"propose":[72],"encoded":[73,138],"(EASRL),":[78],"a":[79,90,94,126,135,142],"method":[82,174],"that":[83,171,182],"learns":[84],"flexible":[85],"latent":[91,121,131,148],"space":[92,160],"for":[93,115],"high-dimensional":[95],"space.":[99,122],"With":[100],"EASRL,":[101],"encoder":[102],"and":[103,161],"decoder":[104],"networks":[105],"trained":[107],"with":[108],"demonstration":[109],"data":[110],"by":[111],"using":[112],"variational":[113],"autoencoders":[114],"mapping":[116],"into":[119],"Then,":[123],"we":[124,150],"learn":[125],"policy":[127],"network":[128],"space,":[132,149],"distribution":[136],"given":[141],"state.":[143],"By":[144],"can":[151],"handle":[162],"various":[163],"patterns":[164],"sequences.":[167],"experimentally":[169],"demonstrate":[170],"proposed":[173],"outperforms":[175],"other":[176],"methods":[179],"tasks":[181],"require":[183],"an":[184],"extensive":[185],"amount":[186],"search.":[188]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}