{"id":"https://openalex.org/W4404699682","doi":"https://doi.org/10.1007/s11063-024-11705-x","title":"Policy Optimization Algorithm with Activation Likelihood-Ratio for Multi-agent Reinforcement Learning","display_name":"Policy Optimization Algorithm with Activation Likelihood-Ratio for Multi-agent Reinforcement Learning","publication_year":2024,"publication_date":"2024-11-25","ids":{"openalex":"https://openalex.org/W4404699682","doi":"https://doi.org/10.1007/s11063-024-11705-x"},"language":"en","primary_location":{"id":"doi:10.1007/s11063-024-11705-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11705-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11705-x.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11705-x.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046320247","display_name":"Lu Jia","orcid":"https://orcid.org/0000-0002-7982-797X"},"institutions":[{"id":"https://openalex.org/I4210118050","display_name":"Taishan University","ror":"https://ror.org/02bpnkx55","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210118050"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lu Jia","raw_affiliation_strings":["College of Physics and Electronic Engineering, Taishan University, Tai\u2019an, China","College of Physics and Electronic Engineering, Taishan University, Tai'an, China"],"raw_orcid":"https://orcid.org/0000-0002-7982-797X","affiliations":[{"raw_affiliation_string":"College of Physics and Electronic Engineering, Taishan University, Tai\u2019an, China","institution_ids":["https://openalex.org/I4210118050"]},{"raw_affiliation_string":"College of Physics and Electronic Engineering, Taishan University, Tai'an, China","institution_ids":["https://openalex.org/I4210118050"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114286104","display_name":"Binglin Su","orcid":null},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binglin Su","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068433690","display_name":"Dongkuan Xu","orcid":"https://orcid.org/0000-0002-1456-9658"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Du Xu","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084203184","display_name":"Yewei Wang","orcid":"https://orcid.org/0000-0003-0302-3411"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yewei Wang","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101590466","display_name":"Jing Fang","orcid":"https://orcid.org/0000-0002-4767-4817"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Fang","raw_affiliation_strings":["School of Computer and Information, Hefei University of Technology, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer and Information, Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100760080","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0002-2086-2500"},"institutions":[{"id":"https://openalex.org/I3132008074","display_name":"Huangshan University","ror":"https://ror.org/05akhmy90","country_code":"CN","type":"education","lineage":["https://openalex.org/I3132008074"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["School of Information Engineering, Huangshan University, Huangshan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Engineering, Huangshan University, Huangshan, China","institution_ids":["https://openalex.org/I3132008074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046320247"],"corresponding_institution_ids":["https://openalex.org/I4210118050"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":0.972,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.80189986,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"56","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9923999905586243,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T14011","display_name":"Elevator Systems and Control","score":0.9878000020980835,"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":0.8228799104690552},{"id":"https://openalex.org/keywords/computational-intelligence","display_name":"Computational intelligence","score":0.6545379161834717},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5532737970352173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5289354920387268},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4328383803367615},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.42631202936172485},{"id":"https://openalex.org/keywords/optimization-algorithm","display_name":"Optimization algorithm","score":0.4217250943183899},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2797466516494751},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17837023735046387},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.10656142234802246}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8228799104690552},{"id":"https://openalex.org/C139502532","wikidata":"https://www.wikidata.org/wiki/Q1122090","display_name":"Computational intelligence","level":2,"score":0.6545379161834717},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5532737970352173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5289354920387268},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4328383803367615},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.42631202936172485},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.4217250943183899},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2797466516494751},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17837023735046387},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.10656142234802246}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11063-024-11705-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11705-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11705-x.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11063-024-11705-x","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11063-024-11705-x","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11063-024-11705-x.pdf","source":{"id":"https://openalex.org/S140962798","display_name":"Neural Processing Letters","issn_l":"1370-4621","issn":["1370-4621","1573-773X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neural Processing Letters","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.49000000953674316}],"awards":[{"id":"https://openalex.org/G6180073671","display_name":null,"funder_award_id":"62101206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404699682.pdf","grobid_xml":"https://content.openalex.org/works/W4404699682.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W180325379","https://openalex.org/W2099618002","https://openalex.org/W2101786389","https://openalex.org/W2125612430","https://openalex.org/W2168359464","https://openalex.org/W2617547828","https://openalex.org/W2747213132","https://openalex.org/W2982316857","https://openalex.org/W2996896271","https://openalex.org/W3013664888","https://openalex.org/W3126698741","https://openalex.org/W3156295478","https://openalex.org/W3174995978","https://openalex.org/W3182648169","https://openalex.org/W4360825542","https://openalex.org/W6600339963","https://openalex.org/W6602646459","https://openalex.org/W6608803649","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","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":{"As":[0],"a":[1,62,82],"ubiquitous":[2],"on-policy":[3],"reinforcement":[4],"learning":[5],"algorithm,":[6],"proximal":[7,113],"policy":[8,34,92,114],"optimization":[9,35,115],"(PPO)":[10],"has":[11],"achieved":[12],"the":[13,28,33,37,104,111,125,136,151],"state-of-the-art":[14],"performance":[15],"in":[16,41,71,110,168,172],"both":[17],"single-agent":[18],"and":[19,30,66,95,122,131,146,157,165],"cooperative":[20,138],"multi-agent":[21,139,173],"scenarios.":[22],"However,":[23],"it":[24,67],"still":[25],"suffers":[26],"from":[27],"instability":[29],"inefficiency":[31],"of":[32,124],"with":[36,116,150,155],"non-strictly":[38],"restricted":[39,60],"likelihood-ratio":[40,51,118],"clipping":[42,74,79,99],"strategy.":[43],"In":[44],"this":[45,55],"work,":[46],"we":[47],"propose":[48],"an":[49],"activation":[50,64,117],"(ALR)":[52],"for":[53],"solving":[54],"issue.":[56],"The":[57,76,97,120],"ALR":[58,78,98],"is":[59,101],"by":[61],"tanh":[63],"function,":[65,107],"can":[68,89],"be":[69],"employed":[70],"multiple":[72],"functional":[73],"strategies.":[75],"resulted":[77],"strategy":[80,100],"produces":[81,144],"smooth":[83],"but":[84],"precipitous":[85],"objective":[86],"curve,":[87],"which":[88],"provide":[90],"high":[91,163],"update":[93],"stationarity":[94],"efficiency.":[96],"incorporated":[102],"into":[103],"PPO":[105,154,158],"loss":[106],"thus":[108],"resulting":[109],"method":[112],"(PPO-ALR).":[119],"rationality":[121],"superiority":[123],"ALR-based":[126],"target":[127],"function":[128],"are":[129],"proved":[130],"analyzed.":[132],"Moreover,":[133],"experiments":[134],"on":[135],"Pistonball":[137],"game":[140],"show":[141],"that":[142],"PPO-ALR":[143],"competitive":[145],"superior":[147],"results":[148],"compared":[149],"standard":[152],"PPO,":[153],"rollback,":[156],"smoothed":[159],"algorithms,":[160],"especially":[161],"its":[162],"efficiency":[164],"success":[166],"probability":[167],"searching":[169],"optimal":[170],"policies":[171],"environments.":[174]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}