{"id":"https://openalex.org/W4405975489","doi":"https://doi.org/10.1109/pimrc59610.2024.10817200","title":"Transfer Learning With Less Negative Transfer for Multi-Agent Reinforcement Learning: Application and Evaluation in Base Station Control","display_name":"Transfer Learning With Less Negative Transfer for Multi-Agent Reinforcement Learning: Application and Evaluation in Base Station Control","publication_year":2024,"publication_date":"2024-09-02","ids":{"openalex":"https://openalex.org/W4405975489","doi":"https://doi.org/10.1109/pimrc59610.2024.10817200"},"language":"en","primary_location":{"id":"doi:10.1109/pimrc59610.2024.10817200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pimrc59610.2024.10817200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 35th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","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/A5050879720","display_name":"M Namiki","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masanobu Namiki","raw_affiliation_strings":["Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026150925","display_name":"Yoshihiro Okawa","orcid":"https://orcid.org/0000-0001-5095-4927"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshihiro Okawa","raw_affiliation_strings":["Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016398372","display_name":"Natsuki Morita","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Natsuki Morita","raw_affiliation_strings":["Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009433353","display_name":"Jun Kakuta","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Kakuta","raw_affiliation_strings":["Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104087241","display_name":"Masatoshi Ogawa","orcid":null},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masatoshi Ogawa","raw_affiliation_strings":["Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588"],"affiliations":[{"raw_affiliation_string":"Fujitsu Limited,Artificial intelligence laboratory,Kawasaki,Kanagawa,Japan,211-8588","institution_ids":["https://openalex.org/I2252096349"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5050879720"],"corresponding_institution_ids":["https://openalex.org/I2252096349"],"apc_list":null,"apc_paid":null,"fwci":0.6989,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73483513,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.8073999881744385,"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"}},"topics":[{"id":"https://openalex.org/T10917","display_name":"Smart Grid Security and Resilience","score":0.8073999881744385,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7778000235557556,"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":0.7751076221466064},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.6750752925872803},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6716909408569336},{"id":"https://openalex.org/keywords/base","display_name":"Base (topology)","score":0.48389968276023865},{"id":"https://openalex.org/keywords/transfer","display_name":"Transfer (computing)","score":0.46906542778015137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3792771100997925},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08698835968971252},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08414533734321594}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7751076221466064},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.6750752925872803},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6716909408569336},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.48389968276023865},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.46906542778015137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3792771100997925},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08698835968971252},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08414533734321594},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/pimrc59610.2024.10817200","is_oa":false,"landing_page_url":"https://doi.org/10.1109/pimrc59610.2024.10817200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 35th International Symposium on Personal, Indoor and Mobile Radio Communications (PIMRC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2129733867","https://openalex.org/W2190432600","https://openalex.org/W2585821313","https://openalex.org/W2807900833","https://openalex.org/W2921955147","https://openalex.org/W2963944430","https://openalex.org/W3014664339","https://openalex.org/W3183673024","https://openalex.org/W3198359393","https://openalex.org/W4251243451","https://openalex.org/W4293095094","https://openalex.org/W4311404181","https://openalex.org/W4362709110","https://openalex.org/W4383112908","https://openalex.org/W6685562342","https://openalex.org/W6737893269","https://openalex.org/W6738796088","https://openalex.org/W6739193204","https://openalex.org/W6783838878","https://openalex.org/W6806989032"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2964765435"],"abstract_inverted_index":{"Deep":[0],"multi-agent":[1,205],"reinforcement":[2,74],"learning":[3,33,46,55,62,66,71,75,85,91,110,115,126,132,194,222],"(DMARL)":[4],"can":[5,218],"derive":[6],"the":[7,37,45,84,97,114,124,136,140,181,200,216,221,226],"optimal":[8,38],"control":[9,206,212],"rules":[10],"for":[11,72,112],"systems":[12],"in":[13,25,69,82,127,151,178],"which":[14,83,128],"multiple":[15],"agents":[16],"interact":[17],"with":[18],"each":[19],"other":[20],"and":[21,159,213,231],"has":[22],"been":[23],"used":[24],"various":[26],"fields.":[27],"Since":[28],"DMARL":[29,50,118],"requires":[30],"a":[31,57,80,107,152,169],"long":[32],"time":[34,116,223],"to":[35,43,48,51,60,157,174,180,184,191,203],"learn":[36],"rules,":[39],"it":[40,188],"is":[41,56,92,103,189],"important":[42],"improve":[44],"efficiency":[47,86],"apply":[49,192,199],"real-world":[52],"problems.":[53],"Transfer":[54],"common":[58],"approach":[59],"reduce":[61,220],"times":[63],"of":[64,99,117,130,143,164,225,228],"deep":[65,73,131],"models.":[67],"However,":[68],"transfer":[70,90,109,125,193],"including":[76,208],"DMARL,":[77],"negative":[78,121,144,196],"transfer,":[79],"phenomenon":[81],"worsens":[87],"even":[88],"though":[89],"applied,":[93],"may":[94],"occur":[95],"when":[96],"degree":[98],"similarity":[100],"between":[101],"tasks":[102,207],"low.":[104],"We":[105,198],"propose":[106],"stable":[108],"method":[111,138,173,183,202,217],"reducing":[113],"by":[119],"preventing":[120],"transfer.":[122,197],"For":[123],"parameters":[129],"models":[133],"are":[134],"reused,":[135],"proposed":[137,201],"eliminates":[139],"two":[141,204],"causes":[142],"transfer:":[145],"(i)":[146],"dead":[147,176],"neurons,":[148],"i.e.,":[149],"neurons":[150,177],"neural":[153],"network":[154],"that":[155,215],"fail":[156],"activate,":[158],"(ii)":[160],"biased":[161],"action":[162],"probabilities":[163],"transferred":[165],"agents.":[166],"By":[167],"applying":[168],"new":[170],"parameter":[171],"reusing":[172],"avoid":[175],"addition":[179],"conventional":[182],"promote":[185],"agent":[186,229],"exploration,":[187],"possible":[190],"without":[195],"base":[209],"station":[210],"sleeping":[211],"show":[214],"stably":[219],"regardless":[224],"type":[227],"model":[230,232],"architecture.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}