{"id":"https://openalex.org/W4411171946","doi":"https://doi.org/10.1109/tcds.2025.3578001","title":"CPIG: Leveraging Consistency Policy With Intention Guidance for Multiagent Exploration","display_name":"CPIG: Leveraging Consistency Policy With Intention Guidance for Multiagent Exploration","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https://openalex.org/W4411171946","doi":"https://doi.org/10.1109/tcds.2025.3578001"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2025.3578001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3578001","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","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/A5109305150","display_name":"Yunzhun Fu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuqian Fu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0008-9031-9889","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080193690","display_name":"Yuanheng Zhu","orcid":"https://orcid.org/0000-0001-5384-423X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanheng Zhu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5384-423X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoran Li","orcid":"https://orcid.org/0000-0003-2559-9585"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Li","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2559-9585","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zijie Zhao","orcid":"https://orcid.org/0000-0001-7756-7046"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijie Zhao","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7756-7046","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073383645","display_name":"Jiajun Chai","orcid":"https://orcid.org/0000-0002-7611-064X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Chai","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7611-064X","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8218-9633","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04985327,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"18","issue":"1","first_page":"154","last_page":"166"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.988099992275238,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.988099992275238,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.96670001745224,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9552000164985657,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.8597844839096069},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.7065778970718384},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.4248518943786621},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.3696707785129547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20970317721366882}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8597844839096069},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.7065778970718384},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.4248518943786621},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3696707785129547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20970317721366882}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2025.3578001","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3578001","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"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 Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7285338662","display_name":null,"funder_award_id":"20240484514","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G800914696","display_name":null,"funder_award_id":"62136008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8179479325","display_name":null,"funder_award_id":"62293541","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"},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2747213132","https://openalex.org/W2803208334","https://openalex.org/W2992005611","https://openalex.org/W3114632476","https://openalex.org/W3210169707","https://openalex.org/W4226440390","https://openalex.org/W4288049695","https://openalex.org/W4319165238","https://openalex.org/W4366310810","https://openalex.org/W4382202883","https://openalex.org/W4385245566","https://openalex.org/W4385488528","https://openalex.org/W4386470330","https://openalex.org/W4387185165","https://openalex.org/W4391974559","https://openalex.org/W4392151673","https://openalex.org/W4392946708","https://openalex.org/W4394698426","https://openalex.org/W4404293755","https://openalex.org/W4405785078","https://openalex.org/W4406158006","https://openalex.org/W4409581282","https://openalex.org/W7124261631","https://openalex.org/W7124280040","https://openalex.org/W7124295897"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Efficient":[0],"exploration":[1,36,103],"is":[2,176,220],"crucial":[3],"in":[4,11,41,178,201,209],"cooperative":[5],"multi-agent":[6,75,179,184],"reinforcement":[7],"learning":[8,67],"(MARL),":[9],"especially":[10],"sparse-reward":[12,42,210],"settings.":[13],"However,":[14],"due":[15],"to":[16,27,47,56,99,112,134,145,198],"the":[17,20,30,34,63,71,101,108,125,147,150,166],"reliance":[18],"on":[19,149],"unimodal":[21],"policy,":[22,126],"existing":[23],"methods":[24],"are":[25],"prone":[26],"falling":[28],"into":[29],"local":[31,156],"optima,":[32],"hindering":[33],"effective":[35],"of":[37,65,74],"better":[38],"policies.":[39],"Furthermore,":[40],"settings,":[43,211],"each":[44,154],"agent":[45,114],"tends":[46],"receive":[48],"a":[49,83,96,121,163],"scarce":[50],"reward,":[51],"which":[52],"poses":[53],"significant":[54],"challenges":[55],"inter-agent":[57],"cooperation.":[58,115],"This":[59,158],"not":[60,193],"only":[61,194],"increases":[62],"difficulty":[64],"policy":[66,98],"but":[68,204],"also":[69,205],"degrades":[70],"overall":[72],"performance":[73,197,208],"tasks.":[76],"To":[77],"address":[78],"these":[79],"issues,":[80],"we":[81,140],"propose":[82],"Consistency":[84,122,167],"Policy":[85],"with":[86,90],"Intention":[87,143],"Guidance":[88],"(CPIG),":[89],"two":[91],"primary":[92],"components:":[93],"(a)":[94],"introducing":[95],"multimodal":[97,129],"enhance":[100],"agent\u2019s":[102,155],"capability,":[104],"and":[105,131,183],"(b)":[106],"sharing":[107],"intention":[109,148,159],"among":[110,171],"agents":[111],"foster":[113],"For":[116],"component":[117,138],"(a),":[118],"CPIG":[119],"incorporates":[120],"model":[123],"as":[124,162],"leveraging":[127],"its":[128],"nature":[130],"stochastic":[132],"characteristics":[133],"facilitate":[135],"exploration.":[136],"Regarding":[137],"(b),":[139],"introduce":[141],"an":[142],"Learner":[144],"deduce":[146],"global":[151],"state":[152],"from":[153],"observation.":[157],"then":[160],"serves":[161],"guidance":[164],"for":[165],"Policy,":[168],"promoting":[169],"cooperation":[170],"agents.":[172],"The":[173,218],"proposed":[174],"method":[175,192],"evaluated":[177],"particle":[180],"environments":[181,203],"(MPE)":[182],"MuJoCo":[185],"(MAMuJoCo).":[186],"Empirical":[187],"results":[188],"demonstrate":[189],"that":[190],"our":[191],"achieves":[195],"comparable":[196],"various":[199],"baselines":[200],"dense-reward":[202],"significantly":[206],"enhances":[207],"outperforming":[212],"state-of-the-art":[213],"(SOTA)":[214],"algorithms":[215],"by":[216],"20%.":[217],"code":[219],"available":[221],"here.":[222]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}