{"id":"https://openalex.org/W4362590704","doi":"https://doi.org/10.1007/s11633-022-1383-7","title":"Offline Pre-trained Multi-agent Decision Transformer","display_name":"Offline Pre-trained Multi-agent Decision Transformer","publication_year":2023,"publication_date":"2023-03-31","ids":{"openalex":"https://openalex.org/W4362590704","doi":"https://doi.org/10.1007/s11633-022-1383-7"},"language":"en","primary_location":{"id":"doi:10.1007/s11633-022-1383-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-022-1383-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-022-1383-7.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11633-022-1383-7.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027592774","display_name":"Linghui Meng","orcid":"https://orcid.org/0000-0002-5826-8072"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linghui Meng","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":"https://orcid.org/0000-0002-5826-8072","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049802452","display_name":"Muning Wen","orcid":"https://orcid.org/0009-0000-7868-1262"},"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":"Muning Wen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, 200240, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039250611","display_name":"Chenyang Le","orcid":null},"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":"Chenyang Le","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, 200240, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091529668","display_name":"Xiyun Li","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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiyun Li","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","School of Future Technology, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Future Technology, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101684094","display_name":"Dengpeng Xing","orcid":"https://orcid.org/0000-0002-8251-9118"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dengpeng Xing","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090720315","display_name":"Weinan Zhang","orcid":"https://orcid.org/0000-0002-0127-2425"},"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":"Weinan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, 200240, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101647485","display_name":"Ying Wen","orcid":"https://orcid.org/0000-0002-6974-5110"},"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":"Ying Wen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, 200240, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, 200240, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399691","display_name":"Haifeng Zhang","orcid":"https://orcid.org/0000-0003-2670-6055"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Zhang","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001861094","display_name":"Jun Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Department of Computer Science, University College London, London, WC1E 6BT, UK"],"raw_orcid":"https://orcid.org/0000-0001-9006-7951","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University College London, London, WC1E 6BT, UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090073634","display_name":"Yaodong Yang","orcid":"https://orcid.org/0000-0001-8132-5613"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaodong Yang","raw_affiliation_strings":["Institute for AI, Peking University, Beijing, 100871, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for AI, Peking University, Beijing, 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108642431","display_name":"Bo Xu","orcid":"https://orcid.org/0000-0002-1111-1529"},"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/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Xu","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China"],"raw_orcid":"https://orcid.org/0000-0002-1111-1529","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China","institution_ids":["https://openalex.org/I4210094879","https://openalex.org/I19820366"]},{"raw_affiliation_string":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":11,"corresponding_author_ids":["https://openalex.org/A5001861094","https://openalex.org/A5108642431"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210094879","https://openalex.org/I4210165038","https://openalex.org/I45129253"],"apc_list":null,"apc_paid":null,"fwci":6.9977,"has_fulltext":true,"cited_by_count":46,"citation_normalized_percentile":{"value":0.97634724,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"20","issue":"2","first_page":"233","last_page":"248"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9714999794960022,"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":0.9430999755859375,"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":0.8093050718307495},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7570086717605591},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6784180402755737},{"id":"https://openalex.org/keywords/online-and-offline","display_name":"Online and offline","score":0.5674434304237366},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5573837161064148},{"id":"https://openalex.org/keywords/offline-learning","display_name":"Offline learning","score":0.5570682287216187},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5188178420066833},{"id":"https://openalex.org/keywords/marl","display_name":"Marl","score":0.4588596820831299},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4277452230453491},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.41803044080734253},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.23910892009735107},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12092176079750061},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.10768535733222961}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8093050718307495},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7570086717605591},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6784180402755737},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.5674434304237366},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5573837161064148},{"id":"https://openalex.org/C2780490138","wikidata":"https://www.wikidata.org/wiki/Q7079636","display_name":"Offline learning","level":3,"score":0.5570682287216187},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5188178420066833},{"id":"https://openalex.org/C92927620","wikidata":"https://www.wikidata.org/wiki/Q184053","display_name":"Marl","level":3,"score":0.4588596820831299},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4277452230453491},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.41803044080734253},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.23910892009735107},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12092176079750061},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.10768535733222961},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11633-022-1383-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-022-1383-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-022-1383-7.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:10168378","is_oa":true,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/10168378/","pdf_url":"https://discovery.ucl.ac.uk/10168378/1/s11633-022-1383-7.pdf","source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"   Machine Intelligence Research , 20  (2)   pp. 233-248.   (2023)      ","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1007/s11633-022-1383-7","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11633-022-1383-7","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11633-022-1383-7.pdf","source":{"id":"https://openalex.org/S4210224602","display_name":"Machine Intelligence Research","issn_l":"2731-538X","issn":["2731-538X","2731-5398"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Intelligence Research","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8294312625","display_name":null,"funder_award_id":"XDA27030300","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4362590704.pdf"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W1583837637","https://openalex.org/W2119717200","https://openalex.org/W2411690432","https://openalex.org/W2530849036","https://openalex.org/W2539402368","https://openalex.org/W2602856279","https://openalex.org/W2622408375","https://openalex.org/W2756196406","https://openalex.org/W2786036274","https://openalex.org/W2794643322","https://openalex.org/W2803005587","https://openalex.org/W2886647275","https://openalex.org/W2892009249","https://openalex.org/W2904246096","https://openalex.org/W2904453761","https://openalex.org/W2911743772","https://openalex.org/W2914154006","https://openalex.org/W2946606218","https://openalex.org/W2947150733","https://openalex.org/W2963542740","https://openalex.org/W2981187905","https://openalex.org/W2996037775","https://openalex.org/W3016525976","https://openalex.org/W3016943563","https://openalex.org/W3022566517","https://openalex.org/W3032916997","https://openalex.org/W3034084488","https://openalex.org/W3035478219","https://openalex.org/W3085267010","https://openalex.org/W3093963693","https://openalex.org/W3094502228","https://openalex.org/W3107615218","https://openalex.org/W3123636359","https://openalex.org/W3130091361","https://openalex.org/W3136237689","https://openalex.org/W3138460475","https://openalex.org/W3138516171","https://openalex.org/W3169291081","https://openalex.org/W3169871130","https://openalex.org/W3171362638","https://openalex.org/W3174153107","https://openalex.org/W3187418919","https://openalex.org/W3189584127","https://openalex.org/W3193711978","https://openalex.org/W3196792970","https://openalex.org/W3197189015","https://openalex.org/W3198396204","https://openalex.org/W3200561352","https://openalex.org/W3203079382","https://openalex.org/W3204192621","https://openalex.org/W3208313084","https://openalex.org/W3213789840","https://openalex.org/W4286748781","https://openalex.org/W4287126489","https://openalex.org/W4301501993","https://openalex.org/W4313156423","https://openalex.org/W4383112908","https://openalex.org/W4387171915","https://openalex.org/W6747941106","https://openalex.org/W6758846586","https://openalex.org/W6767785798","https://openalex.org/W6772005887","https://openalex.org/W6779109570","https://openalex.org/W6791661883","https://openalex.org/W6799166919","https://openalex.org/W6800682094","https://openalex.org/W6802126314"],"related_works":["https://openalex.org/W4225619808","https://openalex.org/W4388926065","https://openalex.org/W4386160446","https://openalex.org/W4387545330","https://openalex.org/W4387293922","https://openalex.org/W4226221094","https://openalex.org/W4221145086","https://openalex.org/W4226042081","https://openalex.org/W92125585","https://openalex.org/W4284974072"],"abstract_inverted_index":{"Abstract":[0],"Offline":[1],"reinforcement":[2,29,225],"learning":[3,30,226],"leverages":[4,172],"previously":[5],"collected":[6],"offline":[7,50,65,103,119,144,169,186,218,224,273],"datasets":[8,61,80],"to":[9,16,84,121,127,235],"learn":[10],"optimal":[11],"policies":[12,201],"with":[13,41,52,133,147,184],"no":[14],"necessity":[15],"access":[17],"the":[18,34,42,47,75,86,89,93,99,106,142,153,159,173,215,222,238,256,263,270],"real":[19],"environment.":[20,43],"Such":[21],"a":[22],"paradigm":[23,48],"is":[24,196,262],"also":[25],"desirable":[26],"for":[27,64,167,177,284],"multi-agent":[28,163],"(MARL)":[31],"tasks,":[32,237],"given":[33],"combinatorially":[35],"increased":[36],"interactions":[37],"among":[38],"agents":[39,113,209],"and":[40,81,114,125,135,156,180,187,231,245,252,268,281],"However,":[44],"in":[45,92,105,249,276],"MARL,":[46],"of":[49,88,95,101,129,162,194,208,258,272,278],"pre-training":[51,104],"online":[53,122,188,236],"fine-tuning":[54],"has":[55],"not":[56],"been":[57],"studied,":[58],"nor":[59],"even":[60],"or":[62],"benchmarks":[63],"MARL":[66,102,145,189],"research":[67,76],"are":[68],"available.":[69],"In":[70],"this":[71,261],"paper,":[72],"we":[73],"facilitate":[74],"by":[77,140],"providing":[78],"large-scale":[79],"using":[82],"them":[83],"examine":[85],"usage":[87],"decision":[90,164],"transformer":[91,165],"context":[94],"MARL.":[96,285],"We":[97,138],"investigate":[98],"generalization":[100],"following":[107],"three":[108],"aspects:":[109],"1)":[110],"between":[111,205],"single":[112],"multiple":[115,130],"agents,":[116],"2)":[117],"from":[118],"pretraining":[120],"fine":[123],"tuning,":[124],"3)":[126],"that":[128,197,202,266],"downstream":[131],"tasks":[132],"few-shot":[134],"zero-shot":[136,253],"capabilities.":[137],"start":[139],"introducing":[141],"first":[143,264],"dataset":[146],"diverse":[148],"quality":[149],"levels":[150],"based":[151],"on":[152],"StarCraftII":[154],"environment,":[155],"then":[157],"propose":[158],"novel":[160],"architecture":[161],"(MADT)":[166],"effective":[168],"learning.":[170],"MADT":[171,195,220,240],"transformer\u2019s":[174],"modelling":[175,179],"ability":[176],"sequence":[178],"integrates":[181],"it":[182,198],"seamlessly":[183],"both":[185,250],"tasks.":[190],"A":[191],"significant":[192],"benefit":[193],"learns":[199],"generalizable":[200],"can":[203],"transfer":[204],"different":[206,211],"types":[207],"under":[210],"task":[212],"scenarios.":[213],"On":[214],"StarCraft":[216],"II":[217],"dataset,":[219],"outperforms":[221],"state-of-the-art":[223],"(RL)":[227],"baselines,":[228],"including":[229],"BCQ":[230],"CQL.":[232],"When":[233],"applied":[234],"pre-trained":[239,274],"significantly":[241],"improves":[242],"sample":[243,279],"efficiency":[244,280],"enjoys":[246],"strong":[247],"performance":[248],"few-short":[251],"cases.":[254],"To":[255],"best":[257],"our":[259],"knowledge,":[260],"work":[265],"studies":[267],"demonstrates":[269],"effectiveness":[271],"models":[275],"terms":[277],"generalizability":[282],"enhancements":[283]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":14},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}
