{"id":"https://openalex.org/W4416748896","doi":"https://doi.org/10.1109/iros60139.2025.11247096","title":"Transformer-Based Multi-Agent Reinforcement Learning Method With Credit-Oriented Strategy Differentiation","display_name":"Transformer-Based Multi-Agent Reinforcement Learning Method With Credit-Oriented Strategy Differentiation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748896","doi":"https://doi.org/10.1109/iros60139.2025.11247096"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","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/A5109343769","display_name":"Kaixuan Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaixuan Huang","raw_affiliation_strings":["Dalian University of Technology,School of Computer Science and Technology,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Computer Science and Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051178997","display_name":"Bo Jin","orcid":"https://orcid.org/0000-0002-4094-7499"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Jin","raw_affiliation_strings":["Dalian University of Technology,School of Computer Science and Technology,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dalian University of Technology,School of Computer Science and Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101884557","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0001-6397-9648"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kun Zhang","raw_affiliation_strings":["Northwestern Polytechnical University,School of Electronics and Information,Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Electronics and Information,Xian,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004540162","display_name":"Haiyin Piao","orcid":"https://orcid.org/0000-0002-8519-4750"},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyin Piao","raw_affiliation_strings":["Northwestern Polytechnical University,School of Electronics and Information,Xian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University,School of Electronics and Information,Xian,China","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079553918","display_name":"Ziqi Wei","orcid":"https://orcid.org/0000-0001-9402-8386"},"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":"Ziqi Wei","raw_affiliation_strings":["Chinese Academy of Sciences,Institute of Automation,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Institute of Automation,Beijing,China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6055","last_page":"6062"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7383999824523926,"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":0.7383999824523926,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.04399999976158142,"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/T14413","display_name":"Advanced Technologies in Various Fields","score":0.02239999920129776,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8813999891281128},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5110999941825867},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.45170000195503235},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4343999922275543},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.43369999527931213},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41659998893737793},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.382999986410141}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8813999891281128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7311999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5623000264167786},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5110999941825867},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.45170000195503235},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4343999922275543},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.43369999527931213},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4302000105381012},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.382999986410141},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.3580999970436096},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247096","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W52153049","https://openalex.org/W2617547828","https://openalex.org/W2997940961","https://openalex.org/W3005761304","https://openalex.org/W4362519817","https://openalex.org/W4382202546","https://openalex.org/W4389473504"],"related_works":[],"abstract_inverted_index":{"The":[0,96,115],"problem":[1],"of":[2,11,48,75,147,167,197,205],"Multi-Agent":[3,61],"Reinforcement":[4,62],"Learning":[5,63],"(MARL)":[6],"shows":[7],"a":[8,59,81,137,195],"high":[9],"level":[10],"both":[12,99],"complexity":[13],"in":[14,45,125],"the":[15,25,46,93,107,130,144,165,172,176,203,206],"environment":[16],"and":[17,53,85,101,186],"coordination":[18],"between":[19],"agents.":[20],"In":[21,56],"order":[22],"to":[23,27,72,112,119,158,190,201],"scale":[24],"algorithm":[26],"large-scale":[28],"agent":[29,149],"scenarios,":[30],"neural":[31],"networks":[32],"designed":[33,118],"for":[34,106],"MARL":[35],"are":[36,199],"typically":[37],"implemented":[38],"with":[39],"parameter":[40],"sharing.":[41],"These":[42],"characteristics":[43],"result":[44],"challenges":[47],"partial":[49,113],"observability,":[50],"credit":[51,131],"assignment":[52,132],"strategy":[54,168],"homogenization.":[55,169],"this":[57],"paper,":[58],"Transformer-Based":[60],"Method":[64],"With":[65],"Credit-Oriented":[66,138],"Strategy":[67,139],"Differentiation":[68,140],"(TMRC)":[69],"is":[70,117,211],"presented":[71],"address":[73],"each":[74,121,148],"these":[76],"challenges.":[77],"First,":[78],"we":[79,135],"design":[80],"Temporal-Spatial":[82],"Encoding":[83],"module":[84,90,141],"an":[86],"Attention-Based":[87],"Value":[88],"Decomposition":[89],"based":[91,150],"on":[92,151,175],"Transformer":[94],"architecture.":[95],"former":[97],"leverages":[98],"temporal":[100],"spatial":[102],"observation":[103],"information,":[104],"compensating":[105],"missing":[108],"environmental":[109],"perspectives":[110],"due":[111],"observability.":[114],"latter":[116],"identify":[120],"agent\u2019s":[122],"individual":[123],"contribution":[124],"complex":[126],"interactions,":[127],"effectively":[128,163],"optimizing":[129],"process.":[133],"Then,":[134],"propose":[136],"that":[142],"differentiates":[143],"entity":[145],"representations":[146],"their":[152],"current":[153],"task":[154],"differences,":[155],"allowing":[156],"agents":[157],"have":[159],"distinct":[160],"real-time":[161],"strategies,":[162],"mitigating":[164],"issue":[166],"We":[170],"evaluate":[171],"proposed":[173,207],"method":[174],"SMAC":[177],"benchmark.":[178],"It":[179],"demonstrates":[180],"better":[181],"final":[182],"performance,":[183],"faster":[184],"convergence,":[185],"greater":[187],"stability":[188],"compared":[189],"other":[191],"comparative":[192],"methods.":[193],"Additionally,":[194],"series":[196],"experiments":[198],"conducted":[200],"validate":[202],"effectiveness":[204],"modules.":[208],"Our":[209],"code":[210],"available":[212],"at":[213],"https://github.com/Hkxuan/TMRC.git.":[214]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-11-28T00:00:00"}