{"id":"https://openalex.org/W4402381621","doi":"https://doi.org/10.1007/s10489-024-05811-5","title":"Uncertainty modified policy for multi-agent reinforcement learning","display_name":"Uncertainty modified policy for multi-agent reinforcement learning","publication_year":2024,"publication_date":"2024-09-09","ids":{"openalex":"https://openalex.org/W4402381621","doi":"https://doi.org/10.1007/s10489-024-05811-5"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-024-05811-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-024-05811-5","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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":"Applied Intelligence","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/A5010590329","display_name":"Xinyu Zhao","orcid":"https://orcid.org/0000-0002-1098-5670"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyu Zhao","raw_affiliation_strings":["Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, 100191, China","Key Laboratory of Mathematics, Informatics and Behavioral Semantics (LMIB), Beihang University, Beijing, 100191, China","School of Mathematical Sciences, Beihang University, 37 Xueyuan Road, Haidian District, Beijing, 100190, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Key Laboratory of Mathematics, Informatics and Behavioral Semantics (LMIB), Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Mathematical Sciences, Beihang University, 37 Xueyuan Road, Haidian District, Beijing, 100190, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101896256","display_name":"Jianxiang Liu","orcid":"https://orcid.org/0000-0002-4379-3288"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxiang Liu","raw_affiliation_strings":["Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, 100191, China","Institute of Artificial Intelligence, Beihang University, 37 Xueyuan Road, Haidian District, Beijing, 100190, China","Key Laboratory of Mathematics, Informatics and Behavioral Semantics (LMIB), Beihang University, Beijing, 100191, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, 37 Xueyuan Road, Haidian District, Beijing, 100190, China","institution_ids":["https://openalex.org/I82880672","https://openalex.org/I4210100255"]},{"raw_affiliation_string":"Key Laboratory of Mathematics, Informatics and Behavioral Semantics (LMIB), Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059360884","display_name":"Faguo Wu","orcid":"https://orcid.org/0000-0002-1878-3547"},"institutions":[{"id":"https://openalex.org/I4210089285","display_name":"Ji Hua Laboratory","ror":"https://ror.org/006aydy55","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210089285"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Faguo Wu","raw_affiliation_strings":["Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, 100191, China","Institute of Artificial Intelligence, Beihang University, 37 Xueyuan Road, Haidian District, Beijing, 100190, China","Key Laboratory of Mathematics, Informatics and Behavioral Semantics (LMIB), Beihang University, Beijing, 100191, China","Zhongguancun Laboratory, Beijing, 100194, China"],"raw_orcid":"https://orcid.org/0000-0002-1878-3547","affiliations":[{"raw_affiliation_string":"Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Beihang University, 37 Xueyuan Road, Haidian District, Beijing, 100190, China","institution_ids":["https://openalex.org/I82880672","https://openalex.org/I4210100255"]},{"raw_affiliation_string":"Key Laboratory of Mathematics, Informatics and Behavioral Semantics (LMIB), Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Zhongguancun Laboratory, Beijing, 100194, China","institution_ids":["https://openalex.org/I4210089285"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101843032","display_name":"Xiao Zhang","orcid":"https://orcid.org/0000-0002-0821-8579"},"institutions":[{"id":"https://openalex.org/I4210089285","display_name":"Ji Hua Laboratory","ror":"https://ror.org/006aydy55","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210089285"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Zhang","raw_affiliation_strings":["Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, 100191, China","Key Laboratory of Mathematics, Informatics and Behavioral Semantics (LMIB), Beihang University, Beijing, 100191, China","School of Mathematical Sciences, Beihang University, 37 Xueyuan Road, Haidian District, Beijing, 100190, China","Zhongguancun Laboratory, Beijing, 100194, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Key Laboratory of Mathematics, Informatics and Behavioral Semantics (LMIB), Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Mathematical Sciences, Beihang University, 37 Xueyuan Road, Haidian District, Beijing, 100190, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Zhongguancun Laboratory, Beijing, 100194, China","institution_ids":["https://openalex.org/I4210089285"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101747036","display_name":"Guojian Wang","orcid":"https://orcid.org/0000-0002-7456-9844"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guojian Wang","raw_affiliation_strings":["Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, 100191, China","Key Laboratory of Mathematics, Informatics and Behavioral Semantics (LMIB), Beihang University, Beijing, 100191, China","School of Mathematical Sciences, Beihang University, 37 Xueyuan Road, Haidian District, Beijing, 100190, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bejing Advanced Innovation Center for Future Blockchain and Privacy Computing, Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Key Laboratory of Mathematics, Informatics and Behavioral Semantics (LMIB), Beihang University, Beijing, 100191, China","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"School of Mathematical Sciences, Beihang University, 37 Xueyuan Road, Haidian District, Beijing, 100190, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5010590329"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":null,"fwci":0.9934,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80277842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"54","issue":"22","first_page":"12020","last_page":"12034"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9987999796867371,"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":0.9987999796867371,"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/T14011","display_name":"Elevator Systems and Control","score":0.992900013923645,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10524","display_name":"Traffic control and management","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9010791778564453},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8503997325897217},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4631039798259735},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.4327145516872406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38173848390579224},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2425539493560791},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.08928424119949341},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05884310603141785}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9010791778564453},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8503997325897217},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4631039798259735},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.4327145516872406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38173848390579224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2425539493560791},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.08928424119949341},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05884310603141785}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-024-05811-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-024-05811-5","pdf_url":null,"source":{"id":"https://openalex.org/S74726891","display_name":"Applied Intelligence","issn_l":"0924-669X","issn":["0924-669X","1573-7497"],"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":"Applied Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G352320128","display_name":null,"funder_award_id":"2022ZD0116401","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G8351431548","display_name":null,"funder_award_id":"62141605","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"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1676314349","https://openalex.org/W1981276685","https://openalex.org/W2186766170","https://openalex.org/W2617547828","https://openalex.org/W2747329762","https://openalex.org/W2968104655","https://openalex.org/W3014596384","https://openalex.org/W3031798691","https://openalex.org/W3035478219","https://openalex.org/W3102100346","https://openalex.org/W3134774296","https://openalex.org/W3164731060","https://openalex.org/W3166816823","https://openalex.org/W3177473096","https://openalex.org/W3194422450","https://openalex.org/W3195835426","https://openalex.org/W3195968524","https://openalex.org/W4221160324","https://openalex.org/W4285278949","https://openalex.org/W4294280793","https://openalex.org/W4307898121","https://openalex.org/W4362650357","https://openalex.org/W4378190882","https://openalex.org/W4381198761","https://openalex.org/W4386280773","https://openalex.org/W4387171915","https://openalex.org/W4390284935"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","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"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
