{"id":"https://openalex.org/W4376505453","doi":"https://doi.org/10.1080/01691864.2023.2208634","title":"Design of restricted normalizing flow towards arbitrary stochastic policy with computational efficiency","display_name":"Design of restricted normalizing flow towards arbitrary stochastic policy with computational efficiency","publication_year":2023,"publication_date":"2023-05-13","ids":{"openalex":"https://openalex.org/W4376505453","doi":"https://doi.org/10.1080/01691864.2023.2208634"},"language":"en","primary_location":{"id":"doi:10.1080/01691864.2023.2208634","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01691864.2023.2208634","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.12894","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051304187","display_name":"Taisuke Kobayashi","orcid":"https://orcid.org/0000-0002-3760-249X"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Taisuke Kobayashi","raw_affiliation_strings":["Principles of Informatics Research Division, National Institute of Informatics, Tokyo, Japan","School of Multidisciplinary Sciences, Department of Informatics, The Graduate University for Advanced Studies (SOKENDAI), Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Principles of Informatics Research Division, National Institute of Informatics, Tokyo, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"School of Multidisciplinary Sciences, Department of Informatics, The Graduate University for Advanced Studies (SOKENDAI), Tokyo, Japan","institution_ids":["https://openalex.org/I200475212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060502779","display_name":"Takumi Aotani","orcid":"https://orcid.org/0000-0002-5774-767X"},"institutions":[{"id":"https://openalex.org/I16656306","display_name":"Meiji University","ror":"https://ror.org/02rqvrp93","country_code":"JP","type":"education","lineage":["https://openalex.org/I16656306"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takumi Aotani","raw_affiliation_strings":["Department of Mechanical Engineering Informatics, School of Science and Technology, Meiji University, Kanagawa, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Mechanical Engineering Informatics, School of Science and Technology, Meiji University, Kanagawa, Japan","institution_ids":["https://openalex.org/I16656306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5051304187"],"corresponding_institution_ids":["https://openalex.org/I184597095","https://openalex.org/I200475212"],"apc_list":null,"apc_paid":null,"fwci":0.6913,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74731291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"37","issue":"12","first_page":"719","last_page":"736"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.96670001745224,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9609000086784363,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/invertible-matrix","display_name":"Invertible matrix","score":0.6453096270561218},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.637323796749115},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.6255736947059631},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6113013029098511},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5989915728569031},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.5114635229110718},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4800375699996948},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4627184271812439},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.45241355895996094},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.32692015171051025},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29882776737213135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2795904278755188},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26946038007736206},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.2616475224494934}],"concepts":[{"id":"https://openalex.org/C96442724","wikidata":"https://www.wikidata.org/wiki/Q242188","display_name":"Invertible matrix","level":2,"score":0.6453096270561218},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.637323796749115},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.6255736947059631},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6113013029098511},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5989915728569031},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.5114635229110718},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4800375699996948},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4627184271812439},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.45241355895996094},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.32692015171051025},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29882776737213135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2795904278755188},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26946038007736206},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2616475224494934},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1080/01691864.2023.2208634","is_oa":false,"landing_page_url":"https://doi.org/10.1080/01691864.2023.2208634","pdf_url":null,"source":{"id":"https://openalex.org/S192584203","display_name":"Advanced Robotics","issn_l":"0169-1864","issn":["0169-1864","1568-5535"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320547","host_organization_name":"Taylor & Francis","host_organization_lineage":["https://openalex.org/P4310320547"],"host_organization_lineage_names":["Taylor & Francis"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advanced Robotics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2412.12894","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.12894","pdf_url":"https://arxiv.org/pdf/2412.12894","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2412.12894","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.12894","pdf_url":"https://arxiv.org/pdf/2412.12894","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":[{"id":"https://metadata.un.org/sdg/17","score":0.4000000059604645,"display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G5518604981","display_name":null,"funder_award_id":"PREST","funder_id":"https://openalex.org/F4320338111","funder_display_name":"Precursory Research for Embryonic Science and Technology"},{"id":"https://openalex.org/G8506408848","display_name":null,"funder_award_id":"JPMJPR20C3","funder_id":"https://openalex.org/F4320338111","funder_display_name":"Precursory Research for Embryonic Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320338111","display_name":"Precursory Research for Embryonic Science and Technology","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4376505453.pdf"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1994616650","https://openalex.org/W2022365837","https://openalex.org/W2047161049","https://openalex.org/W2059374347","https://openalex.org/W2113442785","https://openalex.org/W2120630110","https://openalex.org/W2145339207","https://openalex.org/W2158782408","https://openalex.org/W2172968643","https://openalex.org/W2199578125","https://openalex.org/W2260756217","https://openalex.org/W2594103415","https://openalex.org/W2604382266","https://openalex.org/W2781726626","https://openalex.org/W2900582619","https://openalex.org/W2903866873","https://openalex.org/W2919115771","https://openalex.org/W2946729629","https://openalex.org/W2952021385","https://openalex.org/W2962834855","https://openalex.org/W2962894046","https://openalex.org/W2965215408","https://openalex.org/W3011671166","https://openalex.org/W3035315132","https://openalex.org/W3047371217","https://openalex.org/W3080884797","https://openalex.org/W3104595455","https://openalex.org/W3108832127","https://openalex.org/W3112130166","https://openalex.org/W3113891126","https://openalex.org/W3121110993","https://openalex.org/W3132285497","https://openalex.org/W3144645906","https://openalex.org/W3168354865","https://openalex.org/W3206369550","https://openalex.org/W3210251473","https://openalex.org/W4206513913","https://openalex.org/W4283784039","https://openalex.org/W4320156277","https://openalex.org/W6735677848","https://openalex.org/W6756040250","https://openalex.org/W6756256016"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138","https://openalex.org/W2743976221"],"abstract_inverted_index":{"This":[0,137],"paper":[1,138],"proposes":[2],"a":[3,8,13,27,53,69,92,97,141,185],"new":[4],"design":[5],"method":[6],"for":[7,88,134],"stochastic":[9,94,130],"control":[10],"policy":[11,22,179,194],"using":[12,166],"normalizing":[14],"flow":[15],"(NF).":[16],"In":[17,156,175],"reinforcement":[18],"learning":[19],"(RL),":[20],"the":[21,44,63,73,120,153,158,181,190],"is":[23,84,99,164],"usually":[24],"modeled":[25],"as":[26,96,170],"distribution":[28,169],"model":[29,49,95],"with":[30,58,85],"trainable":[31],"parameters.":[32],"When":[33],"this":[34,162],"parameterization":[35],"has":[36,50],"less":[37],"expressiveness,":[38],"it":[39,57,124,128],"would":[40],"fail":[41],"to":[42,101,117,195],"acquiring":[43],"optimal":[45],"policy.":[46],"A":[47],"mixture":[48],"capability":[51],"of":[52,75,119,192],"universal":[54],"approximation,":[55],"but":[56],"too":[59],"much":[60],"redundancy":[61],"increases":[62],"computational":[64,107],"cost,":[65],"which":[66,83],"can":[67],"become":[68],"bottleneck":[70],"when":[71],"considering":[72],"use":[74],"real-time":[76],"robot":[77,135,187],"control.":[78],"As":[79],"another":[80],"approach,":[81],"NF,":[82],"additional":[86],"parameters":[87],"invertible":[89,121,154],"transformation":[90],"from":[91],"simple":[93],"base,":[98,172],"expected":[100],"exert":[102],"high":[103],"expressiveness":[104,159],"and":[105,123],"lower":[106],"cost.":[108],"However,":[109],"NF":[110,143],"cannot":[111],"compute":[112],"its":[113,171],"mean":[114,149],"analytically":[115],"due":[116],"complexity":[118],"transformation,":[122],"lacks":[125],"reliability":[126],"because":[127],"retains":[129],"behaviors":[131],"after":[132],"deployment":[133],"controller.":[136],"therefore":[139],"designs":[140],"restricted":[142],"(RNF)":[144],"that":[145],"achieves":[146],"an":[147],"analytic":[148],"by":[150,161],"appropriately":[151],"restricting":[152],"transformation.":[155],"addition,":[157],"impaired":[160],"restriction":[163],"regained":[165],"bimodal":[167],"student-t":[168],"so-called":[173],"Bit-RNF.":[174],"RL":[176],"benchmarks,":[177],"Bit-RNF":[178,193],"outperformed":[180],"previous":[182],"models.":[183],"Finally,":[184],"real":[186,196],"experiment":[188],"demonstrated":[189],"applicability":[191],"world.":[197]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2023-05-15T00:00:00"}