{"id":"https://openalex.org/W4402351535","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651100","title":"APC: Predict Global Representation From Local Observation In Multi-Agent Reinforcement Learning","display_name":"APC: Predict Global Representation From Local Observation In Multi-Agent Reinforcement Learning","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351535","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651100"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10651100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5073392887","display_name":"Xiaoyang Li","orcid":"https://orcid.org/0000-0003-4899-0835"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyang Li","raw_affiliation_strings":["University of Science and Technology of China,Department of Automation,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Department of Automation,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101428033","display_name":"Guohua Yang","orcid":"https://orcid.org/0000-0003-4418-6639"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohua Yang","raw_affiliation_strings":["University of Science and Technology of China,Department of Automation,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Department of Automation,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379743","display_name":"Dawei Zhang","orcid":"https://orcid.org/0000-0002-0841-7826"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dawei Zhang","raw_affiliation_strings":["University of Science and Technology of China,Department of Automation,Hefei,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China,Department of Automation,Hefei,China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112613657","display_name":"Jianhua Tao","orcid":"https://orcid.org/0000-0002-9344-6428"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianhua Tao","raw_affiliation_strings":["Tsinghua University,Department of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University,Department of Automation,Beijing,China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9962999820709229,"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":0.9781000018119812,"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":0.8842636346817017},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5872377753257751},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5610478520393372},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5286116003990173},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4568910598754883},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1216198205947876},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.04859209060668945}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8842636346817017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5872377753257751},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5610478520393372},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5286116003990173},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4568910598754883},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1216198205947876},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.04859209060668945},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651100","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10651100","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W206679605","https://openalex.org/W1191599655","https://openalex.org/W1924770834","https://openalex.org/W2104602264","https://openalex.org/W2134779831","https://openalex.org/W2155027007","https://openalex.org/W2194775991","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2736601468","https://openalex.org/W2747213132","https://openalex.org/W2963658727","https://openalex.org/W2963762747","https://openalex.org/W2982316857","https://openalex.org/W2996037775","https://openalex.org/W2997502221","https://openalex.org/W3099689767","https://openalex.org/W3163926178","https://openalex.org/W3175698408","https://openalex.org/W4281622133","https://openalex.org/W4286748781","https://openalex.org/W4287637675","https://openalex.org/W4287755265","https://openalex.org/W4287756582","https://openalex.org/W4288594419","https://openalex.org/W4299802797","https://openalex.org/W4382461758","https://openalex.org/W4385245566","https://openalex.org/W6627932998","https://openalex.org/W6640212811","https://openalex.org/W6675811377","https://openalex.org/W6680096503","https://openalex.org/W6683204974","https://openalex.org/W6721101288","https://openalex.org/W6738796088","https://openalex.org/W6739516088","https://openalex.org/W6741002519","https://openalex.org/W6748910126","https://openalex.org/W6751912414","https://openalex.org/W6758846586","https://openalex.org/W6762491519","https://openalex.org/W6766805167","https://openalex.org/W6772005887","https://openalex.org/W6781750019","https://openalex.org/W6784152626","https://openalex.org/W6784458062","https://openalex.org/W6791079441","https://openalex.org/W6795908048","https://openalex.org/W6797064975","https://openalex.org/W6802002411","https://openalex.org/W6803581605","https://openalex.org/W6838682728","https://openalex.org/W6840380725"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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"],"abstract_inverted_index":{"Multi-agent":[0],"reinforcement":[1],"learning":[2],"(MARL)":[3],"algorithms":[4],"with":[5,58],"sequential":[6],"decision-making":[7],"strategies":[8],"have":[9],"achieved":[10],"great":[11],"success":[12],"in":[13,40,43,72,87,184],"cooperation":[14,147],"tasks":[15,150],"recently.":[16],"To":[17,155],"overcome":[18],"the":[19,83,89,94,104,106,111,118,128,152,157,163,181],"non-stationarity":[20],"problem,":[21],"these":[22,132],"methods":[23],"design":[24],"a":[25],"centralized":[26,98,185],"controller":[27],"that":[28,121,177],"takes":[29,117],"global":[30,46,95,125,133],"observation":[31,61],"as":[32,127],"input":[33],"and":[34,141,170,187,195],"chooses":[35],"actions":[36],"for":[37],"each":[38],"agent":[39],"sequence.":[41],"However,":[42],"most":[44],"scenarios,":[45],"information":[47,71,126],"is":[48],"only":[49,109],"available":[50],"at":[51,62],"training":[52,186],"time,":[53,64],"while":[54],"agents":[55,67,143],"act":[56],"synchronously":[57],"their":[59],"local":[60,101],"execution":[63,189],"which":[65,88],"prevents":[66],"from":[68,100,124],"leveraging":[69],"more":[70],"cooperation.":[73],"In":[74],"this":[75],"paper,":[76],"based":[77],"on":[78,148,165],"actor-critic":[79],"architecture,":[80],"we":[81,161],"propose":[82],"actor-predicts-critic":[84],"(APC)":[85],"algorithm,":[86],"actor":[90,107],"learns":[91],"to":[92,138],"predict":[93],"representations":[96,120,134],"of":[97,159],"critic":[99],"observation.":[102],"During":[103],"training,":[105],"not":[108],"receives":[110],"estimated":[112],"state":[113],"values,":[114],"but":[115],"also":[116],"critic\u2019s":[119],"are":[122,135],"extracted":[123],"prediction":[129],"targets.":[130],"Since":[131],"closely":[136],"related":[137],"agents\u2019":[139],"goals":[140],"rewards,":[142],"can":[144],"achieve":[145],"better":[146],"MARL":[149],"utilizing":[151],"predicted":[153],"representations.":[154],"prove":[156],"validity":[158],"APC,":[160],"evaluate":[162],"algorithm":[164],"StarCraft2,":[166],"Google":[167],"Research":[168],"Football,":[169],"MultiAgent":[171],"Mujoco":[172],"benchmarks.":[173],"The":[174],"results":[175],"show":[176],"APC":[178],"significantly":[179],"outperforms":[180],"strong":[182],"baselines":[183],"decentralized":[188],"(CTDE)":[190],"framework,":[191],"including":[192],"MATDec,":[193],"MAPPO,":[194],"fine-tuned":[196],"QMIX.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}