{"id":"https://openalex.org/W4415568161","doi":"https://doi.org/10.1007/s11432-024-4578-2","title":"Multi-agent robust policy evaluation for reinforcement learning via primal-dual online time-averaging","display_name":"Multi-agent robust policy evaluation for reinforcement learning via primal-dual online time-averaging","publication_year":2025,"publication_date":"2025-10-23","ids":{"openalex":"https://openalex.org/W4415568161","doi":"https://doi.org/10.1007/s11432-024-4578-2"},"language":"en","primary_location":{"id":"doi:10.1007/s11432-024-4578-2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11432-024-4578-2","pdf_url":null,"source":{"id":"https://openalex.org/S4210218743","display_name":"Science China Information Sciences","issn_l":"1674-733X","issn":["1674-733X","1869-1919"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science China Information Sciences","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/A5005160651","display_name":"Gang Chen","orcid":"https://orcid.org/0000-0002-3173-8812"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gang Chen","raw_affiliation_strings":["College of Automation, Chongqing University, Chongqing, 400044, China"],"affiliations":[{"raw_affiliation_string":"College of Automation, Chongqing University, Chongqing, 400044, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092761707","display_name":"Changli Pu","orcid":null},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Changli Pu","raw_affiliation_strings":["College of Automation, Chongqing University, Chongqing, 400044, China"],"affiliations":[{"raw_affiliation_string":"College of Automation, Chongqing University, Chongqing, 400044, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088659212","display_name":"Yaoyao Zhou","orcid":"https://orcid.org/0009-0004-9050-8867"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoyao Zhou","raw_affiliation_strings":["College of Automation, Chongqing University, Chongqing, 400044, China"],"affiliations":[{"raw_affiliation_string":"College of Automation, Chongqing University, Chongqing, 400044, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100652987","display_name":"Xiumin Li","orcid":"https://orcid.org/0000-0002-0512-9642"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiumin Li","raw_affiliation_strings":["College of Automation, Chongqing University, Chongqing, 400044, China"],"affiliations":[{"raw_affiliation_string":"College of Automation, Chongqing University, Chongqing, 400044, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017939066","display_name":"Huimiao Chen","orcid":"https://orcid.org/0009-0009-7760-2097"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huimiao Chen","raw_affiliation_strings":["Tsinghua Laboratory of Brain and Intelligence, Tsinghua University, Beijing, 100084, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua Laboratory of Brain and Intelligence, Tsinghua University, Beijing, 100084, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5005160651"],"corresponding_institution_ids":["https://openalex.org/I158842170"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.33858491,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"68","issue":"12","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9987999796867371,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9968000054359436,"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":0.5432999730110168},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3824000060558319},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.2858999967575073},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.2847000062465668},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.28220000863075256},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.2732999920845032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5777000188827515},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5432999730110168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4562999904155731},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3824000060558319},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28220000863075256},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2732999920845032},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.2680000066757202},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.258899986743927}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11432-024-4578-2","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11432-024-4578-2","pdf_url":null,"source":{"id":"https://openalex.org/S4210218743","display_name":"Science China Information Sciences","issn_l":"1674-733X","issn":["1674-733X","1869-1919"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Science China Information Sciences","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2963128910","https://openalex.org/W3108171015","https://openalex.org/W4200113240"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-28T00:00:00"}
