{"id":"https://openalex.org/W7138916561","doi":"https://doi.org/10.1016/j.engappai.2026.114465","title":"Dynamic residual multi-stage replay policy gradient method for multi-agent cooperation and competition","display_name":"Dynamic residual multi-stage replay policy gradient method for multi-agent cooperation and competition","publication_year":2026,"publication_date":"2026-03-18","ids":{"openalex":"https://openalex.org/W7138916561","doi":"https://doi.org/10.1016/j.engappai.2026.114465"},"language":"en","primary_location":{"id":"doi:10.1016/j.engappai.2026.114465","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.engappai.2026.114465","pdf_url":null,"source":{"id":"https://openalex.org/S900972176","display_name":"Engineering Applications of Artificial Intelligence","issn_l":"0952-1976","issn":["0952-1976","1873-6769"],"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":"Engineering Applications of Artificial 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/A5101573668","display_name":"Xingmei Wang","orcid":"https://orcid.org/0000-0002-0281-0336"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xingmei Wang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0281-0336","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101258520","display_name":"Junzheng Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junzheng Xu","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-3161-7700","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130023160","display_name":"Haotian Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Haotian Li","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0007-5817-6796","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129832008","display_name":"Zining Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zining Yan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-5016-1721","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101573668"],"corresponding_institution_ids":[],"apc_list":{"value":3170,"currency":"USD","value_usd":3170},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57807395,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"174","issue":null,"first_page":"114465","last_page":"114465"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.3366999924182892,"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":0.3366999924182892,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.23430000245571136,"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":0.18389999866485596,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6072999835014343},{"id":"https://openalex.org/keywords/competition","display_name":"Competition (biology)","score":0.5979999899864197},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.2840000092983246},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.2802000045776367},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.2736000120639801}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8810999989509583},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6072999835014343},{"id":"https://openalex.org/C91306197","wikidata":"https://www.wikidata.org/wiki/Q45767","display_name":"Competition (biology)","level":2,"score":0.5979999899864197},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45809999108314514},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.26260000467300415},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24549999833106995},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2321999967098236}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.engappai.2026.114465","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.engappai.2026.114465","pdf_url":null,"source":{"id":"https://openalex.org/S900972176","display_name":"Engineering Applications of Artificial Intelligence","issn_l":"0952-1976","issn":["0952-1976","1873-6769"],"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":"Engineering Applications of Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.40100809931755066,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G1666405140","display_name":null,"funder_award_id":"3072024XX0602","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1542941925","https://openalex.org/W2136848157","https://openalex.org/W2746553466","https://openalex.org/W2761873684","https://openalex.org/W2963079702","https://openalex.org/W2963688947","https://openalex.org/W2963917788","https://openalex.org/W4321763414","https://openalex.org/W4399424069","https://openalex.org/W4410431351"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-03-20T20:54:20.808490","created_date":"2026-03-20T00:00:00"}
