{"id":"https://openalex.org/W4302774844","doi":"https://doi.org/10.23919/sice56594.2022.9905759","title":"On Fast Learning of Cooperative Transport by Multi-robots using DeepDyna-Q","display_name":"On Fast Learning of Cooperative Transport by Multi-robots using DeepDyna-Q","publication_year":2022,"publication_date":"2022-09-06","ids":{"openalex":"https://openalex.org/W4302774844","doi":"https://doi.org/10.23919/sice56594.2022.9905759"},"language":"en","primary_location":{"id":"doi:10.23919/sice56594.2022.9905759","is_oa":false,"landing_page_url":"https://doi.org/10.23919/sice56594.2022.9905759","pdf_url":null,"source":{"id":"https://openalex.org/S4363608498","display_name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","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":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","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/A5089052137","display_name":"Almira Budiyanto","orcid":"https://orcid.org/0000-0002-5173-1466"},"institutions":[{"id":"https://openalex.org/I96036126","display_name":"Kumamoto University","ror":"https://ror.org/02cgss904","country_code":"JP","type":"education","lineage":["https://openalex.org/I96036126"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Almira Budiyanto","raw_affiliation_strings":["Kumamoto University,Graduate School of Science and Technology,Kumamoto,Japan","Graduate School of Science and Technology, Kumamoto University, Kumamoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kumamoto University,Graduate School of Science and Technology,Kumamoto,Japan","institution_ids":["https://openalex.org/I96036126"]},{"raw_affiliation_string":"Graduate School of Science and Technology, Kumamoto University, Kumamoto, Japan","institution_ids":["https://openalex.org/I96036126"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064855309","display_name":"Keisuke Azetsu","orcid":null},"institutions":[{"id":"https://openalex.org/I96036126","display_name":"Kumamoto University","ror":"https://ror.org/02cgss904","country_code":"JP","type":"education","lineage":["https://openalex.org/I96036126"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keisuke Azetsu","raw_affiliation_strings":["Kumamoto University,Graduate School of Science and Technology,Kumamoto,Japan","Graduate School of Science and Technology, Kumamoto University, Kumamoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kumamoto University,Graduate School of Science and Technology,Kumamoto,Japan","institution_ids":["https://openalex.org/I96036126"]},{"raw_affiliation_string":"Graduate School of Science and Technology, Kumamoto University, Kumamoto, Japan","institution_ids":["https://openalex.org/I96036126"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112414907","display_name":"Kenta Miyazaki","orcid":null},"institutions":[{"id":"https://openalex.org/I96036126","display_name":"Kumamoto University","ror":"https://ror.org/02cgss904","country_code":"JP","type":"education","lineage":["https://openalex.org/I96036126"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kenta Miyazaki","raw_affiliation_strings":["Kumamoto University,Graduate School of Science and Technology,Kumamoto,Japan","Graduate School of Science and Technology, Kumamoto University, Kumamoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kumamoto University,Graduate School of Science and Technology,Kumamoto,Japan","institution_ids":["https://openalex.org/I96036126"]},{"raw_affiliation_string":"Graduate School of Science and Technology, Kumamoto University, Kumamoto, Japan","institution_ids":["https://openalex.org/I96036126"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025823182","display_name":"Nobutomo Matsunaga","orcid":"https://orcid.org/0009-0000-8211-8376"},"institutions":[{"id":"https://openalex.org/I96036126","display_name":"Kumamoto University","ror":"https://ror.org/02cgss904","country_code":"JP","type":"education","lineage":["https://openalex.org/I96036126"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutomo Matsunaga","raw_affiliation_strings":["Kumamoto University,Faculty of Advanced Science and Technology,Kumamoto,Japan","Faculty of Advanced Science and Technology, Kumamoto University, Kumamoto, Japan"],"affiliations":[{"raw_affiliation_string":"Kumamoto University,Faculty of Advanced Science and Technology,Kumamoto,Japan","institution_ids":["https://openalex.org/I96036126"]},{"raw_affiliation_string":"Faculty of Advanced Science and Technology, Kumamoto University, Kumamoto, Japan","institution_ids":["https://openalex.org/I96036126"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089052137"],"corresponding_institution_ids":["https://openalex.org/I96036126"],"apc_list":null,"apc_paid":null,"fwci":0.2096,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42664829,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1058","last_page":"1062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.996999979019165,"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":0.996999979019165,"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/T11942","display_name":"Transportation and Mobility Innovations","score":0.974399983882904,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T10524","display_name":"Traffic control and management","score":0.9541000127792358,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8624383211135864},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6718319058418274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6430355906486511},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.5720381140708923},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5147559642791748},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4560905992984772},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.34752392768859863}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8624383211135864},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6718319058418274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6430355906486511},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.5720381140708923},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5147559642791748},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4560905992984772},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34752392768859863}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/sice56594.2022.9905759","is_oa":false,"landing_page_url":"https://doi.org/10.23919/sice56594.2022.9905759","pdf_url":null,"source":{"id":"https://openalex.org/S4363608498","display_name":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","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":"2022 61st Annual Conference of the Society of Instrument and Control Engineers (SICE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1568318154","https://openalex.org/W1573357502","https://openalex.org/W2145339207","https://openalex.org/W2783543950","https://openalex.org/W4200315052","https://openalex.org/W4254038002","https://openalex.org/W4299802797","https://openalex.org/W6633984492","https://openalex.org/W6738796088","https://openalex.org/W6747812028","https://openalex.org/W6759490492"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W4380075502","https://openalex.org/W4376605461","https://openalex.org/W2357975469","https://openalex.org/W2136202932","https://openalex.org/W3087814763","https://openalex.org/W2892507673","https://openalex.org/W2361647908","https://openalex.org/W2937181779","https://openalex.org/W2537866915"],"abstract_inverted_index":{"In":[0,54],"recent":[1],"years,":[2],"there":[3],"have":[4],"been":[5,37,52],"many":[6],"studies":[7,149],"on":[8],"cooperative":[9,68],"transport.":[10],"Reinforcement":[11],"learning":[12,21,27,30,35,49,58,61,77,80,161,168],"has":[13,36,51],"attracted":[14],"attention":[15],"for":[16,39],"formation":[17,65,87,107],"changes.":[18],"As":[19,127],"reinforcement":[20,57],"requires":[22],"a":[23,47,120,154],"large":[24],"number":[25,97],"of":[26,67,98,135],"cycles,":[28],"fast":[29],"algorithms":[31],"are":[32],"needed.":[33],"Model-based":[34],"studied":[38],"unknown":[40],"environments":[41],"to":[42,64,78,85,104,152,162],"learn":[43],"efficiently.":[44],"Deep":[45,73,93,112],"Dyna-Q,":[46],"model-based":[48,60,76,160],"method,":[50],"proposed.":[53],"this":[55],"paper,":[56],"using":[59,75],"is":[62,146],"applied":[63,83],"changes":[66],"transportations.":[69],"This":[70],"study":[71],"constructed":[72],"Dyna-Q":[74,94,113],"improve":[79],"speed":[81],"and":[82,123,167],"it":[84,128],"robot":[86],"change.":[88],"The":[89,106],"results":[90],"showed":[91],"that":[92,131,158],"improved":[95],"the":[96,132,136,143],"episodes":[99],"by":[100],"about":[101],"half":[102],"compared":[103],"DQN.":[105],"change":[108],"achievement":[109,133,165],"rate":[110,134,145,166],"in":[111,116,142],"was":[114,124,129,138],"74%":[115],"an":[117,140],"environment":[118],"with":[119],"transport":[121],"object":[122],"slightly":[125],"low.":[126],"reported":[130],"literature":[137],"99%,":[139],"improvement":[141],"success":[144],"desired.":[147],"Future":[148],"should":[150],"aim":[151],"use":[153],"multi-agent":[155],"algorithm":[156],"MADDPG":[157],"uses":[159],"achieve":[163],"both":[164],"time.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-18T14:38:29.013473","created_date":"2025-10-10T00:00:00"}