{"id":"https://openalex.org/W4405785484","doi":"https://doi.org/10.1109/iros58592.2024.10802580","title":"Transformer-based Multi-Agent Reinforcement Learning for Generalization of Heterogeneous Multi-Robot Cooperation","display_name":"Transformer-based Multi-Agent Reinforcement Learning for Generalization of Heterogeneous Multi-Robot Cooperation","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785484","doi":"https://doi.org/10.1109/iros58592.2024.10802580"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-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/A5088549136","display_name":"Yuxin Cai","orcid":"https://orcid.org/0000-0002-5628-7050"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yuxin Cai","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061259393","display_name":"Xiangkun He","orcid":"https://orcid.org/0000-0001-9818-0879"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Xiangkun He","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100971197","display_name":"Hongliang Guo","orcid":null},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hongliang Guo","raw_affiliation_strings":["Agency for Science, Technology and Research (ASTAR),Institute for Infocomm Research (I2R),Singapore"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research (ASTAR),Institute for Infocomm Research (I2R),Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057104857","display_name":"Wei\u2010Yun Yau","orcid":"https://orcid.org/0000-0001-5709-9169"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wei-Yun Yau","raw_affiliation_strings":["Agency for Science, Technology and Research (ASTAR),Institute for Infocomm Research (I2R),Singapore"],"affiliations":[{"raw_affiliation_string":"Agency for Science, Technology and Research (ASTAR),Institute for Infocomm Research (I2R),Singapore","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I115228651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072073374","display_name":"Chen Lv","orcid":"https://orcid.org/0000-0001-6897-4512"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chen Lv","raw_affiliation_strings":["Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Mechanical and Aerospace Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088549136"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.7252,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78081822,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"13695","last_page":"13702"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7373999953269958,"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":0.7373999953269958,"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":0.810275673866272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6692221164703369},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6410495638847351},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.625371515750885},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5292508006095886},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5092562437057495},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4135358929634094},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14581242203712463},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.133745014667511},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.09728917479515076},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.06711497902870178},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06071072816848755}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.810275673866272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6692221164703369},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6410495638847351},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.625371515750885},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5292508006095886},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5092562437057495},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4135358929634094},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14581242203712463},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.133745014667511},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.09728917479515076},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.06711497902870178},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06071072816848755},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802580","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802580","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311687","display_name":"Ministry of Education","ror":"https://ror.org/03m01yf64"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1996542214","https://openalex.org/W2119981134","https://openalex.org/W2150076638","https://openalex.org/W2747213132","https://openalex.org/W2768629321","https://openalex.org/W2883532348","https://openalex.org/W2891520517","https://openalex.org/W2936516903","https://openalex.org/W2967053680","https://openalex.org/W3003535010","https://openalex.org/W3088990421","https://openalex.org/W3196869853","https://openalex.org/W4210389721","https://openalex.org/W4285792173","https://openalex.org/W4293768836","https://openalex.org/W4362519817","https://openalex.org/W4365800856","https://openalex.org/W4385245566","https://openalex.org/W4389666004","https://openalex.org/W4390099915","https://openalex.org/W4391070002","https://openalex.org/W4391529044","https://openalex.org/W6627932998","https://openalex.org/W6631026904","https://openalex.org/W6684921986","https://openalex.org/W6738796088","https://openalex.org/W6763173156","https://openalex.org/W6766805167","https://openalex.org/W6789172296","https://openalex.org/W6791079441","https://openalex.org/W6795139234","https://openalex.org/W6800682094","https://openalex.org/W6810655720","https://openalex.org/W6838682728","https://openalex.org/W6840380725","https://openalex.org/W6848782485","https://openalex.org/W6861038554"],"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/W2501594388"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,116,142,150],"multi-agent":[3],"reinforcement":[4],"learning":[5],"(MARL)":[6],"have":[7],"significantly":[8],"enhanced":[9],"cooperation":[10,140],"capabilities":[11,128],"within":[12],"multi-robot":[13,174],"teams.":[14],"However,":[15],"the":[16,22,86],"application":[17],"to":[18,30,54,83,95,113,165],"heterogeneous":[19,71,90,139],"teams":[20,31,50],"poses":[21],"critical":[23],"challenge":[24,42],"of":[25,35],"combinatorial":[26],"generalization\u2014adapting":[27],"learned":[28],"policies":[29],"with":[32],"new":[33],"compositions":[34],"varying":[36,127],"sizes":[37],"and":[38,57,80,129,145,153],"robots":[39],"capabilities.":[40,155],"This":[41],"is":[43,111],"paramount":[44],"for":[45,70,172],"dynamic":[46],"real-world":[47,146,173],"scenarios":[48,141],"where":[49],"must":[51],"swiftly":[52],"adapt":[53],"changing":[55],"environmental":[56],"task":[58],"conditions.":[59],"To":[60],"address":[61],"this,":[62],"we":[63,133],"introduce":[64],"a":[65,108],"novel":[66],"transformer-based":[67],"MARL":[68,167],"method":[69,136],"multirobot":[72],"cooperation.":[73],"Our":[74],"approach":[75],"leverages":[76],"graph":[77],"neural":[78],"networks":[79],"self-attention":[81],"mechanisms":[82],"effectively":[84],"capture":[85],"intricate":[87],"dynamics":[88],"among":[89],"robots,":[91],"facilitating":[92],"policy":[93],"adaptation":[94],"team":[96,103,151],"size":[97],"variations.":[98],"Moreover,":[99],"by":[100],"treating":[101],"robot":[102,154],"decisions":[104],"as":[105],"sequential":[106],"inputs,":[107],"capability-oriented":[109],"decoder":[110],"introduced":[112],"generate":[114],"actions":[115],"an":[117],"auto-regressive":[118],"manner,":[119],"enabling":[120],"decentralized":[121],"decision-making":[122],"that":[123],"tailored":[124],"each":[125],"robot\u2019s":[126],"heterogeneity":[130],"type.":[131],"Furthermore,":[132],"evaluate":[134],"our":[135,159],"across":[137],"two":[138],"both":[143],"simulated":[144],"environments,":[147],"featuring":[148],"variations":[149],"number":[152],"Comparative":[156],"results":[157],"reveal":[158],"method\u2019s":[160],"superior":[161],"generalization":[162],"performance":[163],"compared":[164],"existing":[166],"methodologies,":[168],"marking":[169],"its":[170],"potential":[171],"applications.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T23:12:01.093139","created_date":"2025-10-10T00:00:00"}