{"id":"https://openalex.org/W4391559291","doi":"https://doi.org/10.1109/tetci.2024.3359039","title":"Time-Varying Weights in Multi-Reward Architecture for Deep Reinforcement Learning","display_name":"Time-Varying Weights in Multi-Reward Architecture for Deep Reinforcement Learning","publication_year":2024,"publication_date":"2024-02-06","ids":{"openalex":"https://openalex.org/W4391559291","doi":"https://doi.org/10.1109/tetci.2024.3359039"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2024.3359039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3359039","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-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/A5100771701","display_name":"Meng Xu","orcid":"https://orcid.org/0000-0003-4857-5439"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Meng Xu","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-4857-5439","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071933192","display_name":"Xinhong Chen","orcid":"https://orcid.org/0000-0002-8563-148X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xinhong Chen","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-8563-148X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056036421","display_name":"Yechao She","orcid":"https://orcid.org/0000-0002-6951-2392"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yechao She","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-6951-2392","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101925661","display_name":"Jin Yang","orcid":"https://orcid.org/0000-0002-5337-487X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yang Jin","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-5337-487X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100356291","display_name":"Jianping Wang","orcid":"https://orcid.org/0000-0002-9318-1482"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jianping Wang","raw_affiliation_strings":["Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-9318-1482","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of Hong Kong, Kowloon, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":2.2228,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88716205,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"8","issue":"2","first_page":"1865","last_page":"1881"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9894999861717224,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9825999736785889,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7534726858139038},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6391844153404236},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6070372462272644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5051069855690002},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4827967882156372},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3521728515625},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.3240037262439728},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.1648992896080017},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06522619724273682}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7534726858139038},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6391844153404236},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6070372462272644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5051069855690002},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4827967882156372},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3521728515625},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3240037262439728},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.1648992896080017},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06522619724273682},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2024.3359039","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3359039","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1973156346","https://openalex.org/W2145339207","https://openalex.org/W2554120691","https://openalex.org/W2624731731","https://openalex.org/W2746553466","https://openalex.org/W2795921402","https://openalex.org/W2896267617","https://openalex.org/W2950395671","https://openalex.org/W2962244319","https://openalex.org/W2990211277","https://openalex.org/W2991137823","https://openalex.org/W3031447301","https://openalex.org/W3035825996","https://openalex.org/W3091277626","https://openalex.org/W3103559770","https://openalex.org/W3111064853","https://openalex.org/W3126384422","https://openalex.org/W3129151492","https://openalex.org/W3132143347","https://openalex.org/W3206390859","https://openalex.org/W4225131922","https://openalex.org/W4286751599","https://openalex.org/W4298857966","https://openalex.org/W4309669389","https://openalex.org/W4315784722","https://openalex.org/W6616173779","https://openalex.org/W6637967152","https://openalex.org/W6638209102","https://openalex.org/W6677939520","https://openalex.org/W6679365036","https://openalex.org/W6692846177","https://openalex.org/W6729958650","https://openalex.org/W6732665253","https://openalex.org/W6735579001","https://openalex.org/W6740801417","https://openalex.org/W6748638692","https://openalex.org/W6754554871","https://openalex.org/W6773521587","https://openalex.org/W6777834836","https://openalex.org/W6785276508","https://openalex.org/W6787348641","https://openalex.org/W6803341758"],"related_works":["https://openalex.org/W2920061524","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"Deep":[0],"Reinforcement":[1],"Learning":[2],"(DRL)":[3],"has":[4],"recently":[5],"been":[6],"focused":[7],"on":[8,65],"extracting":[9],"more":[10],"knowledge":[11],"from":[12,73,148],"the":[13,29,75,106,140,154,158,164,190,203],"reward":[14,31,142],"signal":[15],"to":[16,104,118,126,139,146,171,188],"improve":[17,127],"sample":[18],"efficiency.":[19],"The":[20],"Multi-Reward":[21],"Architecture":[22],"(MRA)":[23],"achieves":[24],"this":[25,84,120],"by":[26,157],"breaking":[27],"down":[28],"original":[30,141,159],"function":[32],"into":[33,184],"multiple":[34],"sub-reward":[35,150],"branches":[36,53],"and":[37,88,224],"training":[38],"a":[39,59,86,114,135,185],"source-specific":[40,51],"policy":[41,52,136,177,192],"branch":[42,78,95,137,151,193],"for":[43,93,110,175,194],"each":[44,94,149],"one.":[45],"However,":[46],"existing":[47],"MRAs":[48],"treat":[49],"all":[50,176],"as":[54],"equally":[55],"important":[56,77],"or":[57],"assign":[58],"constant":[60],"level":[61],"of":[62,91,217],"importance":[63,108],"based":[64],"current":[66],"task":[67,81,97],"conditions,":[68],"which":[69,122],"hinders":[70],"DRL":[71],"agents":[72],"prioritizing":[74],"most":[76],"at":[79],"different":[80],"stages.":[82],"Additionally,":[83],"necessitates":[85],"manual":[87],"time-consuming":[89],"reset":[90],"weights":[92,174,180],"when":[96],"conditions":[98],"change.":[99],"Thus,":[100],"it":[101],"is":[102],"crucial":[103],"automate":[105],"time-varying":[107,173],"assignment":[109],"branches.":[111,178],"We":[112],"propose":[113],"generic":[115],"MRA":[116,130,145,210],"approach":[117],"achieve":[119],"goal,":[121],"can":[123],"be":[124],"applied":[125],"state-of-the-art":[128],"(SOTA)":[129],"methods.":[131],"Firstly,":[132],"we":[133,162],"add":[134],"corresponding":[138],"function,":[143],"allowing":[144],"learn":[147,172],"without":[152],"losing":[153],"experience":[155],"provided":[156],"reward.":[160],"Then,":[161],"apply":[163],"Asynchronous":[165],"Advantage":[166],"Actor":[167],"Critic":[168],"(A3C)":[169],"algorithm":[170],"These":[179],"are":[181],"then":[182],"shaped":[183],"one-hot":[186],"vector":[187],"select":[189],"suitable":[191],"producing":[195],"an":[196],"action.":[197],"Extensive":[198],"experiments":[199],"have":[200],"demonstrated":[201],"that":[202],"proposed":[204],"method":[205],"effectively":[206],"improves":[207],"three":[208],"SOTA":[209],"methods":[211],"across":[212],"four":[213],"tasks":[214],"in":[215],"terms":[216],"episode":[218,225],"reward,":[219],"success":[220],"rate,":[221],"score":[222],"difference,":[223],"duration.":[226]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}