{"id":"https://openalex.org/W3011728953","doi":"https://doi.org/10.1109/sii46433.2020.9026225","title":"Reinforcement Learning Method with Internal World Model Training","display_name":"Reinforcement Learning Method with Internal World Model Training","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3011728953","doi":"https://doi.org/10.1109/sii46433.2020.9026225","mag":"3011728953"},"language":"en","primary_location":{"id":"doi:10.1109/sii46433.2020.9026225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii46433.2020.9026225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/SICE International Symposium on System Integration (SII)","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/A5065419096","display_name":"Kenji Hirata","orcid":"https://orcid.org/0000-0003-0036-8975"},"institutions":[{"id":"https://openalex.org/I159165171","display_name":"Hokkaido Information University","ror":"https://ror.org/00nyxpe17","country_code":"JP","type":"education","lineage":["https://openalex.org/I159165171"]},{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Kenji Hirata","raw_affiliation_strings":["Graduate School of Information Science and Technology, Hokkaido University, Hokkaido, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University, Hokkaido, Japan","institution_ids":["https://openalex.org/I159165171","https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020353235","display_name":"Hiroyuki Iizuka","orcid":"https://orcid.org/0000-0003-3212-7850"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]},{"id":"https://openalex.org/I159165171","display_name":"Hokkaido Information University","ror":"https://ror.org/00nyxpe17","country_code":"JP","type":"education","lineage":["https://openalex.org/I159165171"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hiroyuki Iizuka","raw_affiliation_strings":["Graduate School of Information Science and Technology, Hokkaido University, Hokkaido, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University, Hokkaido, Japan","institution_ids":["https://openalex.org/I159165171","https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101572257","display_name":"Masahito Yamamoto","orcid":"https://orcid.org/0000-0002-7326-3691"},"institutions":[{"id":"https://openalex.org/I159165171","display_name":"Hokkaido Information University","ror":"https://ror.org/00nyxpe17","country_code":"JP","type":"education","lineage":["https://openalex.org/I159165171"]},{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masahito Yamamoto","raw_affiliation_strings":["Graduate School of Information Science and Technology, Hokkaido University, Hokkaido, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University, Hokkaido, Japan","institution_ids":["https://openalex.org/I159165171","https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065419096"],"corresponding_institution_ids":["https://openalex.org/I159165171","https://openalex.org/I205349734"],"apc_list":null,"apc_paid":null,"fwci":0.1326,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.51331098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"5187540","issue":null,"first_page":"201","last_page":"204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.704800009727478,"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":0.704800009727478,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8537383675575256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7473531365394592},{"id":"https://openalex.org/keywords/train","display_name":"Train","score":0.6082484722137451},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5590655207633972},{"id":"https://openalex.org/keywords/internal-model","display_name":"Internal model","score":0.55727618932724},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.5417497754096985},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4912099242210388},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48907142877578735},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.47360849380493164},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44453227519989014},{"id":"https://openalex.org/keywords/simulation","display_name":"Simulation","score":0.39773690700531006},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.13810598850250244}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8537383675575256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7473531365394592},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.6082484722137451},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5590655207633972},{"id":"https://openalex.org/C28427503","wikidata":"https://www.wikidata.org/wiki/Q13580300","display_name":"Internal model","level":3,"score":0.55727618932724},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.5417497754096985},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4912099242210388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48907142877578735},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.47360849380493164},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44453227519989014},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.39773690700531006},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.13810598850250244},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/sii46433.2020.9026225","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sii46433.2020.9026225","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE/SICE International Symposium on System Integration (SII)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2766447205","https://openalex.org/W2964327849","https://openalex.org/W2982388247","https://openalex.org/W4294560979","https://openalex.org/W6748392304","https://openalex.org/W6748400484","https://openalex.org/W6767611374"],"related_works":["https://openalex.org/W2745063183","https://openalex.org/W618248309","https://openalex.org/W2377336366","https://openalex.org/W1601203902","https://openalex.org/W2102464536","https://openalex.org/W2361332776","https://openalex.org/W4225671779","https://openalex.org/W2733539336","https://openalex.org/W2689112224","https://openalex.org/W1593091151"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,26,34],"can":[2],"be":[3],"applied":[4],"to":[5,45,82],"various":[6],"tasks":[7],"such":[8],"as":[9],"developing":[10],"motion":[11],"controllers":[12],"for":[13,33],"humanoid":[14],"or":[15],"insect-like":[16],"robots,":[17],"playing":[18],"board":[19],"games":[20],"and":[21,70],"video":[22],"games.":[23],"However,":[24],"reinforcement":[25],"requires":[27],"a":[28,53,73,89],"large":[29],"number":[30],"of":[31,49],"trials":[32],"appropriate":[35],"behaviors":[36],"in":[37,72,80,84],"an":[38],"environment":[39,69,75],"that":[40],"required":[41],"physics":[42],"simulations":[43],"due":[44],"the":[46,63,68,77,85,91,94],"computational":[47],"costs":[48],"simulations.":[50],"We":[51],"propose":[52],"model":[54,65,79],"inspired":[55],"by":[56,76],"human":[57],"brain":[58],"simulation.":[59],"The":[60],"agent":[61,92],"builds":[62],"internal":[64,78],"based":[66],"on":[67],"trains":[71],"simulated":[74],"addition":[81],"training":[83],"actual":[86],"environment.":[87],"As":[88],"result,":[90],"acquires":[93],"walking":[95],"movement":[96],"with":[97],"fewer":[98],"trials.":[99]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}