{"id":"https://openalex.org/W4206518134","doi":"https://doi.org/10.1109/smc52423.2021.9658890","title":"Shared Trained Models Selection and Management for Transfer Reinforcement Learning in Open IoT","display_name":"Shared Trained Models Selection and Management for Transfer Reinforcement Learning in Open IoT","publication_year":2021,"publication_date":"2021-10-17","ids":{"openalex":"https://openalex.org/W4206518134","doi":"https://doi.org/10.1109/smc52423.2021.9658890"},"language":"en","primary_location":{"id":"doi:10.1109/smc52423.2021.9658890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9658890","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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/A5022669249","display_name":"Hirofumi Noguchi","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Noguchi","raw_affiliation_strings":["Nippon Telegraph and Telephone Corporation,NTT Network Innovation Center,Tokyo,Japan,180-8585"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation,NTT Network Innovation Center,Tokyo,Japan,180-8585","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021739090","display_name":"Takuma Isoda","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takuma Isoda","raw_affiliation_strings":["NTT DOCOMO,R&D Innovation Division,Kanagawa,Japan,239-8536"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT DOCOMO,R&D Innovation Division,Kanagawa,Japan,239-8536","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072098251","display_name":"Seisuke Arai","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Seisuke Arai","raw_affiliation_strings":["Nippon Telegraph and Telephone Corporation,NTT Network Innovation Center,Tokyo,Japan,180-8585"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nippon Telegraph and Telephone Corporation,NTT Network Innovation Center,Tokyo,Japan,180-8585","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.20221811,"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":"2170","last_page":"2176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T12784","display_name":"Modular Robots and Swarm Intelligence","score":0.9973999857902527,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/T12288","display_name":"Optimization and Search Problems","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.8161357641220093},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7818244099617004},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.7386602163314819},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6441339254379272},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6238111257553101},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5871989727020264},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.582271158695221},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4837353527545929},{"id":"https://openalex.org/keywords/robot-learning","display_name":"Robot learning","score":0.4728779196739197},{"id":"https://openalex.org/keywords/inductive-transfer","display_name":"Inductive transfer","score":0.4630468189716339},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3741776943206787},{"id":"https://openalex.org/keywords/mobile-robot","display_name":"Mobile robot","score":0.16797849535942078},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09121200442314148}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8161357641220093},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7818244099617004},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.7386602163314819},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6441339254379272},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6238111257553101},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5871989727020264},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.582271158695221},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4837353527545929},{"id":"https://openalex.org/C188888258","wikidata":"https://www.wikidata.org/wiki/Q7353390","display_name":"Robot learning","level":4,"score":0.4728779196739197},{"id":"https://openalex.org/C77075516","wikidata":"https://www.wikidata.org/wiki/Q6027324","display_name":"Inductive transfer","level":5,"score":0.4630468189716339},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3741776943206787},{"id":"https://openalex.org/C19966478","wikidata":"https://www.wikidata.org/wiki/Q4810574","display_name":"Mobile robot","level":3,"score":0.16797849535942078},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09121200442314148},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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":1,"locations":[{"id":"doi:10.1109/smc52423.2021.9658890","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc52423.2021.9658890","pdf_url":null,"source":{"id":"https://openalex.org/S4363607761","display_name":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":34,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2090302437","https://openalex.org/W2145339207","https://openalex.org/W2166856083","https://openalex.org/W2167340365","https://openalex.org/W2189162242","https://openalex.org/W2257979135","https://openalex.org/W2413863213","https://openalex.org/W2542642724","https://openalex.org/W2575705757","https://openalex.org/W2601322194","https://openalex.org/W2604763608","https://openalex.org/W2606433045","https://openalex.org/W2735995851","https://openalex.org/W2803767077","https://openalex.org/W2810785043","https://openalex.org/W2949929714","https://openalex.org/W2963428623","https://openalex.org/W2963703448","https://openalex.org/W2964043796","https://openalex.org/W2964227312","https://openalex.org/W3003242083","https://openalex.org/W4235773083","https://openalex.org/W6637373629","https://openalex.org/W6684218820","https://openalex.org/W6687241523","https://openalex.org/W6692846177","https://openalex.org/W6727349600","https://openalex.org/W6735944222","https://openalex.org/W6736368053","https://openalex.org/W6740879895","https://openalex.org/W6751869817","https://openalex.org/W6753243525","https://openalex.org/W6760036574"],"related_works":["https://openalex.org/W3016888008","https://openalex.org/W4394633951","https://openalex.org/W2745420784","https://openalex.org/W4213035857","https://openalex.org/W4387770285","https://openalex.org/W2930863966","https://openalex.org/W4292367956","https://openalex.org/W4312257007","https://openalex.org/W206237318","https://openalex.org/W2158618075"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2,16],"a":[3,17,111,138],"new":[4],"paradigm":[5],"that":[6],"utilizes":[7],"trained":[8,77,86,122],"models":[9,81,123],"shared":[10,37,62,80],"by":[11,163,172,207],"multiple":[12,64,83,186],"systems":[13,34,70,106,206],"and":[14,25,45,57,73,198],"also":[15],"mandatory":[18],"method":[19,68,103,133,166,192],"to":[20,31,71,107,146],"achieve":[21],"it.":[22],"Reinforcement":[23],"learning":[24,27,58,109,126,140,188,195],"transfer":[26,74,161,179,214],"are":[28,51],"powerful":[29],"technologies":[30],"automatically":[32],"build":[33],"composed":[35],"of":[36,42,93,96,99,114,121,152,159,170,202,204],"devices":[38],"with":[39,110,175,210],"various":[40,147],"combinations":[41],"installation":[43],"positions":[44],"device":[46],"types.":[47],"However,":[48],"current":[49],"works":[50],"premised":[52],"on":[53,90,137,185],"an":[54,75,118],"individual":[55,105],"system,":[56],"knowledge":[59],"is":[60,88],"not":[61,135],"across":[63,82],"systems.":[65,84,148],"Our":[66],"proposed":[67,102,132,165,191],"enables":[69,104],"select":[72],"appropriate":[76,119],"model":[78,87,127,162,196],"from":[79],"The":[85,101],"selected":[89],"the":[91,94,125,131,150,153,157,160,164,168,178,190,194,200,211],"basis":[92],"similarity":[95],"input":[97],"data":[98],"learning.":[100,215],"complete":[108],"small":[112],"number":[113,120],"demonstrations":[115],"while":[116],"maintaining":[117],"in":[124,183],"pool.":[128],"Moreover,":[129],"since":[130],"does":[134],"depend":[136],"specific":[139],"algorithm,":[141],"it":[142],"can":[143],"be":[144],"applied":[145],"In":[149,181],"simulation":[151],"robot":[154],"navigation":[155],"task,":[156],"selection":[158],"increased":[167,199],"sum":[169,201],"rewards":[171,203],"32%":[173],"compared":[174,209],"randomly":[176],"selecting":[177],"model.":[180],"addition,":[182],"experiments":[184],"successive":[187],"requests,":[189],"updated":[193],"pool":[197],"all":[205],"34%":[208],"case":[212],"without":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}