{"id":"https://openalex.org/W7127072153","doi":"https://doi.org/10.1007/s00530-025-02153-1","title":"TSPPO: transformer-based sequential proximal policy optimization for multi-agent systems","display_name":"TSPPO: transformer-based sequential proximal policy optimization for multi-agent systems","publication_year":2026,"publication_date":"2026-02-03","ids":{"openalex":"https://openalex.org/W7127072153","doi":"https://doi.org/10.1007/s00530-025-02153-1"},"language":"en","primary_location":{"id":"doi:10.1007/s00530-025-02153-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00530-025-02153-1","pdf_url":null,"source":{"id":"https://openalex.org/S112262039","display_name":"Multimedia Systems","issn_l":"0942-4962","issn":["0942-4962","1432-1882"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Systems","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":"https://openalex.org/A5124758323","display_name":"Tao Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210095659","display_name":"Peking University Stomatological Hospital","ror":"https://ror.org/00s2xkh70","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210095659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Yang","raw_affiliation_strings":["Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China","Beijing Qiangqiang Yuanqiang Technology Co., Ltd, Beijing, 100101, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China","institution_ids":["https://openalex.org/I114234892"]},{"raw_affiliation_string":"Beijing Qiangqiang Yuanqiang Technology Co., Ltd, Beijing, 100101, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210095659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124828306","display_name":"Yuxiao Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210095659","display_name":"Peking University Stomatological Hospital","ror":"https://ror.org/00s2xkh70","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210095659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxiao Gao","raw_affiliation_strings":["Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China","Beijing Qiangqiang Yuanqiang Technology Co., Ltd, Beijing, 100101, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China","institution_ids":["https://openalex.org/I114234892"]},{"raw_affiliation_string":"Beijing Qiangqiang Yuanqiang Technology Co., Ltd, Beijing, 100101, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210095659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124834399","display_name":"Cheng Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210095659","display_name":"Peking University Stomatological Hospital","ror":"https://ror.org/00s2xkh70","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210095659"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Cheng Xu","raw_affiliation_strings":["Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China","Beijing Qiangqiang Yuanqiang Technology Co., Ltd, Beijing, 100101, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China","institution_ids":["https://openalex.org/I114234892"]},{"raw_affiliation_string":"Beijing Qiangqiang Yuanqiang Technology Co., Ltd, Beijing, 100101, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210095659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124839456","display_name":"Hongzhe Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I114234892","display_name":"Beijing Union University","ror":"https://ror.org/01hg31662","country_code":"CN","type":"education","lineage":["https://openalex.org/I114234892"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210095659","display_name":"Peking University Stomatological Hospital","ror":"https://ror.org/00s2xkh70","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210095659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongzhe Liu","raw_affiliation_strings":["Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China","Beijing Qiangqiang Yuanqiang Technology Co., Ltd, Beijing, 100101, China"],"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China","institution_ids":["https://openalex.org/I114234892"]},{"raw_affiliation_string":"Beijing Qiangqiang Yuanqiang Technology Co., Ltd, Beijing, 100101, China","institution_ids":["https://openalex.org/I20231570","https://openalex.org/I4210095659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5124834399"],"corresponding_institution_ids":["https://openalex.org/I114234892","https://openalex.org/I20231570","https://openalex.org/I4210095659"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24760917,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"2","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9351999759674072,"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":0.9351999759674072,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.013799999840557575,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.0066999997943639755,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6940000057220459},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6039999723434448},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5493000149726868},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.40790000557899475},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.3885999917984009},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.3612000048160553},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3598000109195709},{"id":"https://openalex.org/keywords/resource-allocation","display_name":"Resource allocation","score":0.3452000021934509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8259999752044678},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6940000057220459},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6039999723434448},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42879998683929443},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.40790000557899475},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3885999917984009},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3720000088214874},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.328000009059906},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3192000091075897},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.29030001163482666},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00530-025-02153-1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00530-025-02153-1","pdf_url":null,"source":{"id":"https://openalex.org/S112262039","display_name":"Multimedia Systems","issn_l":"0942-4962","issn":["0942-4962","1432-1882"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Multimedia Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5432078838348389,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G7707611072","display_name":null,"funder_award_id":"62171042, U24A20331","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W108417620","https://openalex.org/W1531725372","https://openalex.org/W2000769684","https://openalex.org/W2088956500","https://openalex.org/W2148998091","https://openalex.org/W2807741983","https://openalex.org/W3159196909","https://openalex.org/W3167061096","https://openalex.org/W3168892396","https://openalex.org/W4207021923","https://openalex.org/W4212872294","https://openalex.org/W4223553258","https://openalex.org/W4234761190","https://openalex.org/W4323030862","https://openalex.org/W4367310109","https://openalex.org/W4375869261","https://openalex.org/W4385833503","https://openalex.org/W4390754695","https://openalex.org/W4391721641","https://openalex.org/W4392347726","https://openalex.org/W4395030794","https://openalex.org/W4400275678","https://openalex.org/W4401069840","https://openalex.org/W4401354861"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2026-02-03T00:00:00"}
