{"id":"https://openalex.org/W7160397266","doi":"https://doi.org/10.1007/s10489-026-07255-5","title":"Robust minimax multi-agent deep deterministic policy gradient for reward uncertainty","display_name":"Robust minimax multi-agent deep deterministic policy gradient for reward uncertainty","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W7160397266","doi":"https://doi.org/10.1007/s10489-026-07255-5"},"language":"en","primary_location":{"id":"doi:10.1007/s10489-026-07255-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-026-07255-5","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/A5135529811","display_name":"Daicheng Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Daicheng Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135494962","display_name":"Qiming Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiming Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135443272","display_name":"Yixuan Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yixuan Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135522586","display_name":"Haoxuan Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haoxuan Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135458384","display_name":"Jingwen Chong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jingwen Chong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135511900","display_name":"Li Song","orcid":"https://orcid.org/0000-0002-4888-6045"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Song","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4888-6045","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5135529811"],"corresponding_institution_ids":[],"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":0.94433241,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"56","issue":"7","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":0.5813999772071838,"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":0.5813999772071838,"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/T11413","display_name":"Risk and Portfolio Optimization","score":0.10100000351667404,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09109999984502792,"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/minimax","display_name":"Minimax","score":0.777899980545044},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.33469998836517334},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.28769999742507935},{"id":"https://openalex.org/keywords/robust-optimization","display_name":"Robust optimization","score":0.27720001339912415},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.2597000002861023}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8657000064849854},{"id":"https://openalex.org/C149728462","wikidata":"https://www.wikidata.org/wiki/Q751319","display_name":"Minimax","level":2,"score":0.777899980545044},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5393000245094299},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.33469998836517334},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3100000023841858},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C51152595","wikidata":"https://www.wikidata.org/wiki/Q7882501","display_name":"Uncertainty theory","level":2,"score":0.2442999929189682}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10489-026-07255-5","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s10489-026-07255-5","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":[{"score":0.5165053606033325,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G144150555","display_name":null,"funder_award_id":"52302416","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W2011538677","https://openalex.org/W2149254449","https://openalex.org/W2157721649","https://openalex.org/W2167325835","https://openalex.org/W2257979135","https://openalex.org/W2575731723","https://openalex.org/W2604763608","https://openalex.org/W2788195014","https://openalex.org/W2810602713","https://openalex.org/W2904455790","https://openalex.org/W2963390138","https://openalex.org/W2982316857","https://openalex.org/W3090736043","https://openalex.org/W3127047144","https://openalex.org/W4293580221","https://openalex.org/W4406612093","https://openalex.org/W6891822287"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-05-07T06:12:12.454206","created_date":"2026-05-07T00:00:00"}