{"id":"https://openalex.org/W7143629099","doi":"https://doi.org/10.1016/j.neucom.2026.133478","title":"Curiosity-driven decision causal-convolutional transformer with adaptive training for offline-to-online multi-agent reinforcement learning","display_name":"Curiosity-driven decision causal-convolutional transformer with adaptive training for offline-to-online multi-agent reinforcement learning","publication_year":2026,"publication_date":"2026-03-31","ids":{"openalex":"https://openalex.org/W7143629099","doi":"https://doi.org/10.1016/j.neucom.2026.133478"},"language":"en","primary_location":{"id":"doi:10.1016/j.neucom.2026.133478","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133478","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","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":null,"display_name":"Bohang Shi","orcid":"https://orcid.org/0009-0009-5781-4068"},"institutions":[{"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":false,"raw_author_name":"Bohang Shi","raw_affiliation_strings":["School of Information and Communications Engineering, Faculty of Electronic and Information Engineering, Xi\u2018an Jiaotong University (XJTU), Xi\u2019an, 710049, Shaanxi, China"],"raw_orcid":"https://orcid.org/0009-0009-5781-4068","affiliations":[{"raw_affiliation_string":"School of Information and Communications Engineering, Faculty of Electronic and Information Engineering, Xi\u2018an Jiaotong University (XJTU), Xi\u2019an, 710049, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004322083","display_name":"Weiqiang Jin","orcid":"https://orcid.org/0000-0002-6656-6061"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]},{"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"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Weiqiang Jin","raw_affiliation_strings":["Department of Computer Science and Engineering (CSE), The Chinese University of Hong Kong (CUHK), Shatin, New Territories, 999077, Hong Kong Special Administrative Region of China","Department of Electrical and Electronic Engineering, University of Hong Kong (HKU), Pokfulam, 999077, Hong Kong Special Administrative Region of China","School of Information and Communications Engineering, Faculty of Electronic and Information Engineering, Xi\u2018an Jiaotong University (XJTU), Xi\u2019an, 710049, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-6656-6061","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering (CSE), The Chinese University of Hong Kong (CUHK), Shatin, New Territories, 999077, Hong Kong Special Administrative Region of China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, University of Hong Kong (HKU), Pokfulam, 999077, Hong Kong Special Administrative Region of China","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"School of Information and Communications Engineering, Faculty of Electronic and Information Engineering, Xi\u2018an Jiaotong University (XJTU), Xi\u2019an, 710049, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5131094716","display_name":"Biao Zhao","orcid":null},"institutions":[{"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":"Biao Zhao","raw_affiliation_strings":["School of Information and Communications Engineering, Faculty of Electronic and Information Engineering, Xi\u2018an Jiaotong University (XJTU), Xi\u2019an, 710049, Shaanxi, China"],"raw_orcid":"https://orcid.org/0000-0002-3651-0702","affiliations":[{"raw_affiliation_string":"School of Information and Communications Engineering, Faculty of Electronic and Information Engineering, Xi\u2018an Jiaotong University (XJTU), Xi\u2019an, 710049, Shaanxi, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5131094716"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":{"value":2470,"currency":"USD","value_usd":2470},"apc_paid":null,"fwci":12.1051,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.97853494,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"684","issue":null,"first_page":"133478","last_page":"133478"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5133000016212463,"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":0.5133000016212463,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0706000030040741,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.024800000712275505,"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":0.7275000214576721},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6240000128746033},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4607999920845032},{"id":"https://openalex.org/keywords/adaptive-learning","display_name":"Adaptive learning","score":0.36880001425743103},{"id":"https://openalex.org/keywords/adaptive-control","display_name":"Adaptive control","score":0.33180001378059387},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.32499998807907104},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.31150001287460327}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7498000264167786},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7275000214576721},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6240000128746033},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5608000159263611},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4607999920845032},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45590001344680786},{"id":"https://openalex.org/C125014702","wikidata":"https://www.wikidata.org/wiki/Q4680749","display_name":"Adaptive learning","level":2,"score":0.36880001425743103},{"id":"https://openalex.org/C107464732","wikidata":"https://www.wikidata.org/wiki/Q235781","display_name":"Adaptive control","level":3,"score":0.33180001378059387},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.2847000062465668},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.2791000008583069},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C84839998","wikidata":"https://www.wikidata.org/wiki/Q5249245","display_name":"Decision rule","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C199190896","wikidata":"https://www.wikidata.org/wiki/Q3509276","display_name":"Learning classifier system","level":3,"score":0.25119999051094055},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.25110000371932983},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.neucom.2026.133478","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.neucom.2026.133478","pdf_url":null,"source":{"id":"https://openalex.org/S45693802","display_name":"Neurocomputing","issn_l":"0925-2312","issn":["0925-2312","1872-8286"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Neurocomputing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5406113862991333,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2807741983","https://openalex.org/W3087576197","https://openalex.org/W3156295478","https://openalex.org/W4294811378","https://openalex.org/W4296913591","https://openalex.org/W4296935111","https://openalex.org/W4360584316","https://openalex.org/W4362519817","https://openalex.org/W4362590704","https://openalex.org/W4365444201","https://openalex.org/W4368377635","https://openalex.org/W4381420200","https://openalex.org/W4399697107","https://openalex.org/W4404840317","https://openalex.org/W4405145750","https://openalex.org/W4411194290","https://openalex.org/W7124245009"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2026-04-01T00:00:00"}
