{"id":"https://openalex.org/W4386607612","doi":"https://doi.org/10.1145/3623405","title":"Dynamic Weights and Prior Reward in Policy Fusion for Compound Agent Learning","display_name":"Dynamic Weights and Prior Reward in Policy Fusion for Compound Agent Learning","publication_year":2023,"publication_date":"2023-09-11","ids":{"openalex":"https://openalex.org/W4386607612","doi":"https://doi.org/10.1145/3623405"},"language":"en","primary_location":{"id":"doi:10.1145/3623405","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3623405","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3623405","source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3623405","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, China"],"raw_orcid":"https://orcid.org/0000-0003-4857-5439","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of 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, China"],"raw_orcid":"https://orcid.org/0000-0002-6951-2392","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of 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, China"],"raw_orcid":"https://orcid.org/0000-0002-5337-487X","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of 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, China"],"raw_orcid":"https://orcid.org/0000-0002-9318-1482","affiliations":[{"raw_affiliation_string":"Department of Computer Science, City University of 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":0.5231,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.7214555,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"14","issue":"6","first_page":"1","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9993000030517578,"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":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.994700014591217,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9886000156402588,"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/computer-science","display_name":"Computer science","score":0.8420102000236511},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8183750510215759},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7465089559555054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6597965359687805},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.6510758399963379},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.555472195148468},{"id":"https://openalex.org/keywords/fusion","display_name":"Fusion","score":0.4373437762260437},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4111672043800354}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8420102000236511},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8183750510215759},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7465089559555054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6597965359687805},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6510758399963379},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.555472195148468},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.4373437762260437},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4111672043800354},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3623405","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3623405","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3623405","source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3623405","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3623405","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3623405","source":{"id":"https://openalex.org/S2492086750","display_name":"ACM Transactions on Intelligent Systems and Technology","issn_l":"2157-6904","issn":["2157-6904","2157-6912"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Intelligent Systems and Technology","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386607612.pdf","grobid_xml":"https://content.openalex.org/works/W4386607612.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W2012204020","https://openalex.org/W2144576818","https://openalex.org/W2145339207","https://openalex.org/W2341164098","https://openalex.org/W2533806771","https://openalex.org/W2739330054","https://openalex.org/W2791797404","https://openalex.org/W2905567628","https://openalex.org/W2920329255","https://openalex.org/W2955060956","https://openalex.org/W2964118262","https://openalex.org/W2964118342","https://openalex.org/W2969489701","https://openalex.org/W2970742710","https://openalex.org/W2990211277","https://openalex.org/W3003817470","https://openalex.org/W3004094900","https://openalex.org/W3004325772","https://openalex.org/W3005889076","https://openalex.org/W3006499227","https://openalex.org/W3016392643","https://openalex.org/W3026486560","https://openalex.org/W3036329728","https://openalex.org/W3093528669","https://openalex.org/W3111064853","https://openalex.org/W3138876624","https://openalex.org/W3155473317","https://openalex.org/W3155995476","https://openalex.org/W4230167402","https://openalex.org/W4247678187","https://openalex.org/W4285165559","https://openalex.org/W4285600354","https://openalex.org/W4286751599","https://openalex.org/W4318962912","https://openalex.org/W4387698707"],"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":{"In":[0],"Deep":[1],"Reinforcement":[2],"Learning":[3,83],"(DRL)":[4],"domain,":[5],"a":[6,17,73,101,110,165],"compound":[7,134],"learning":[8,197],"task":[9,52,120,214],"is":[10,174],"often":[11],"decomposed":[12],"into":[13],"several":[14],"sub-tasks":[15,48,63,106,137],"in":[16,131,211],"divide-and-conquer":[18],"manner,":[19],"each":[20],"trained":[21],"separately":[22],"and":[23,87,113,218],"then":[24,144],"fused":[25,124],"concurrently":[26],"to":[27,33,79,91,107,126,146,176],"achieve":[28],"the":[29,38,45,51,55,58,93,115,118,123,129,133,139,148,152,161,171,178,201],"original":[30,153],"task,":[31],"referred":[32,78],"as":[34,80,164],"policy":[35,41,75,150,179,208],"fusion.":[36],"However,":[37],"state-of-the-art":[39],"(SOTA)":[40],"fusion":[42,76,180,186,209],"methods":[43,210],"treat":[44],"importance":[46],"of":[47,57,96,213],"equally":[49],"throughout":[50,117],"process,":[53,121],"eliminating":[54],"possibility":[56],"agent":[59,130],"relying":[60],"on":[61],"different":[62],"at":[64,160],"various":[65],"stages.":[66],"To":[67],"address":[68],"this":[69,183],"limitation,":[70],"we":[71,156],"propose":[72],"generic":[74],"approach,":[77],"Policy":[81],"Fusion":[82],"with":[84,138,170],"Dynamic":[85],"Weights":[86],"Prior":[88],"Reward":[89],"(PFLDWPR),":[90],"automate":[92],"time-varying":[94,102],"selection":[95],"sub-tasks.":[97],"Specifically,":[98],"PFLDWPR":[99],"produces":[100],"one-hot":[103,141],"vector":[104,142],"for":[105,151],"dynamically":[108],"select":[109],"suitable":[111],"sub-task":[112],"mask":[114],"rest":[116],"entire":[119],"enabling":[122],"strategy":[125],"optimally":[127],"guide":[128],"executing":[132],"task.":[135,154],"The":[136],"dynamic":[140],"are":[143],"aggregated":[145],"obtain":[147],"action":[149],"Moreover,":[155],"collect":[157],"sub-tasks\u2019s":[158],"rewards":[159],"pre-training":[162],"stage":[163],"prior":[166,190],"reward,":[167,173,217],"which,":[168],"along":[169],"current":[172],"used":[175],"train":[177],"network.":[181],"Thus,":[182],"approach":[184],"reduces":[185],"bias":[187],"by":[188],"leveraging":[189],"experience.":[191],"Experimental":[192],"results":[193],"under":[194],"three":[195,206],"popular":[196],"tasks":[198],"demonstrate":[199],"that":[200],"proposed":[202],"method":[203],"significantly":[204],"improves":[205],"SOTA":[207],"terms":[212],"duration,":[215],"episode":[216],"score":[219],"difference.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}