{"id":"https://openalex.org/W7203660745","doi":"https://doi.org/10.1016/j.birob.2026.100362","title":"CG-MARL: Human-in-the-loop cognition-guided credit assignment for distributed multi-agent reinforcement learning","display_name":"CG-MARL: Human-in-the-loop cognition-guided credit assignment for distributed multi-agent reinforcement learning","publication_year":2026,"publication_date":"2026-08-01","ids":{"openalex":"https://openalex.org/W7203660745","doi":"https://doi.org/10.1016/j.birob.2026.100362"},"language":"en","primary_location":{"id":"doi:10.1016/j.birob.2026.100362","doi":"https://doi.org/10.1016/j.birob.2026.100362","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.birob.2026.100362","pdf_url":null,"source":{"id":"https://openalex.org/S4210216266","display_name":"Biomimetic Intelligence and Robotics","issn_l":"2097-0242","issn":["2097-0242","2667-3797"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","oarl"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"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":"Biomimetic Intelligence and Robotics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.birob.2026.100362","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159917012","display_name":"Jinxuan Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinxuan Shi","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120411772","display_name":"Zihan Zhao","orcid":"https://orcid.org/0009-0004-0916-0913","observed_orcids":["https://orcid.org/0009-0004-0916-0913"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zihan Zhao","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101943488","display_name":"Anqi Guo","orcid":"https://orcid.org/0000-0002-0914-935X","observed_orcids":["https://orcid.org/0000-0002-0914-935X"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Anqi Guo","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147396024","display_name":"Jiajing Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajing Shi","raw_affiliation_strings":["School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147393737","display_name":"Fei Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei Wang","raw_affiliation_strings":["Southwest China Research Institute of Electronic Equipment, Chengdu 610036, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest China Research Institute of Electronic Equipment, Chengdu 610036, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147417507","display_name":"Liang Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang Li","raw_affiliation_strings":["Southwest China Research Institute of Electronic Equipment, Chengdu 610036, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest China Research Institute of Electronic Equipment, Chengdu 610036, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147378064","display_name":"Qian Su","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian Su","raw_affiliation_strings":["Southwest China Research Institute of Electronic Equipment, Chengdu 610036, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southwest China Research Institute of Electronic Equipment, Chengdu 610036, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100462338","display_name":"Zhe Liu","orcid":"https://orcid.org/0000-0001-6753-0303","observed_orcids":["https://orcid.org/0000-0001-6753-0303","https://orcid.org/0000-0001-7335-3024"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhe Liu","raw_affiliation_strings":["National Key Laboratory of Human\u2013Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China","School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China"],"raw_orcid":"https://orcid.org/0000-0001-6753-0303","affiliations":[{"raw_affiliation_string":"National Key Laboratory of Human\u2013Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China","institution_ids":["https://openalex.org/I87445476"]},{"raw_affiliation_string":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai 200240, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100462338"],"corresponding_institution_ids":["https://openalex.org/I183067930","https://openalex.org/I87445476"],"apc_list":{"value":1800,"currency":"USD","value_usd":1800},"apc_paid":{"value":1800,"currency":"USD","value_usd":1800},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.52168885,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"100362","last_page":"100362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.0,"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/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/credit-assignment","display_name":"credit assignment","score":0.734000027179718},{"id":"https://openalex.org/keywords/human-in-the-loop","display_name":"human-in-the-loop","score":0.8360000252723694},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.5289999842643738},{"id":"https://openalex.org/keywords/human-robot-interaction","display_name":"human-robot interaction","score":0.5350000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5627999901771545},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.430400013923645},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.birob.2026.100362","doi":"https://doi.org/10.1016/j.birob.2026.100362","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.birob.2026.100362","pdf_url":null,"source":{"id":"https://openalex.org/S4210216266","display_name":"Biomimetic Intelligence and Robotics","issn_l":"2097-0242","issn":["2097-0242","2667-3797"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","oarl"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"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":"Biomimetic Intelligence and Robotics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1016/j.birob.2026.100362","doi":"https://doi.org/10.1016/j.birob.2026.100362","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.birob.2026.100362","pdf_url":null,"source":{"id":"https://openalex.org/S4210216266","display_name":"Biomimetic Intelligence and Robotics","issn_l":"2097-0242","issn":["2097-0242","2667-3797"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["cwts-core","doaj","dongbi-d","oarl"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"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":"Biomimetic Intelligence and Robotics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G3518718467","display_name":null,"funder_award_id":"62303307","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G811599038","display_name":null,"funder_award_id":"HMHAI-202408","funder_id":"https://openalex.org/F1015963508","funder_display_name":"Xi'an Jiaotong University"}],"funders":[{"id":"https://openalex.org/F1015963508","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2013784666","https://openalex.org/W2073231946","https://openalex.org/W2161061197","https://openalex.org/W2807741983","https://openalex.org/W2810602713","https://openalex.org/W2908261578","https://openalex.org/W2915117209","https://openalex.org/W2982316857","https://openalex.org/W3212907084","https://openalex.org/W7124286243","https://openalex.org/W7133211372","https://openalex.org/W7133226216","https://openalex.org/W7133230429","https://openalex.org/W7133238541"],"related_works":["https://openalex.org/W6999586323","https://openalex.org/W3158243338","https://openalex.org/W7166866776","https://openalex.org/W7133230201","https://openalex.org/W2891663723","https://openalex.org/W3114419174","https://openalex.org/W6922333513","https://openalex.org/W7165922431","https://openalex.org/W6922558524","https://openalex.org/W7159599013"],"abstract_inverted_index":{"Credit":[0],"assignment":[1,35],"remains":[2],"a":[3,32,81,86],"key":[4],"challenge":[5],"in":[6],"cooperative":[7,64,88],"multi-agent":[8,156],"reinforcement":[9],"learning":[10],"(MARL),":[11],"as":[12],"existing":[13],"methods":[14],"infer":[15],"agent":[16],"contributions":[17,40,108],"indirectly":[18],"from":[19,42],"global":[20,56],"rewards":[21],"through":[22,50],"restrictive":[23],"structural":[24],"assumptions.":[25,133],"We":[26,71],"propose":[27],"Cognition":[28],"Guided":[29],"MARL":[30],"(CG-MARL),":[31],"preference-driven":[33],"credit":[34,99,129,152],"framework":[36],"that":[37],"learns":[38],"agent-wise":[39],"directly":[41],"trajectory-level":[43],"human":[44,114],"preferences.":[45],"Human":[46],"feedback":[47,74],"is":[48],"provided":[49],"pairwise":[51],"trajectory":[52],"comparisons":[53],"with":[54,145],"both":[55],"and":[57,122,142,162],"agent-level":[58,107],"annotations,":[59],"capturing":[60],"holistic":[61],"judgments":[62],"over":[63],"behavior":[65],"without":[66],"requiring":[67],"dense":[68],"environment-defined":[69],"rewards.":[70],"model":[72],"such":[73],"using":[75],"an":[76],"agent-aware":[77],"preference":[78,115],"predictor":[79],"under":[80],"Bradley\u2013Terry":[82],"formulation,":[83],"which":[84],"induces":[85],"preference-aligned":[87,104],"value":[89],"landscape.":[90],"On":[91],"this":[92],"induced":[93],"value,":[94],"we":[95],"perform":[96],"Shapley":[97,126],"value-based":[98],"attribution":[100,130],"to":[101,120],"systematically":[102],"decompose":[103],"cooperation":[105],"into":[106],"via":[109],"counterfactual":[110],"coalition":[111],"reasoning.":[112],"Crucially,":[113],"signals":[116],"are":[117],"further":[118,158],"used":[119],"supervise":[121],"regularize":[123],"the":[124,148],"resulting":[125],"credits,":[127],"grounding":[128],"beyond":[131,164],"architectural":[132],"Extensive":[134],"experiments":[135,157],"on":[136],"SMAC":[137],"demonstrate":[138],"consistent":[139],"performance":[140],"gains":[141],"improved":[143],"coordination,":[144],"ablations":[146],"validating":[147],"effectiveness":[149],"of":[150],"cognition-guided":[151],"assignment.":[153],"Besides,":[154],"real-world":[155],"confirm":[159],"its":[160],"generalization":[161],"robustness":[163],"simulation.":[165]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-08-19T00:00:00"}
