{"id":"https://openalex.org/W4387496102","doi":"https://doi.org/10.1007/s00521-023-08882-6","title":"Hierarchical multi-agent reinforcement learning for cooperative tasks with sparse rewards in continuous domain","display_name":"Hierarchical multi-agent reinforcement learning for cooperative tasks with sparse rewards in continuous domain","publication_year":2023,"publication_date":"2023-10-10","ids":{"openalex":"https://openalex.org/W4387496102","doi":"https://doi.org/10.1007/s00521-023-08882-6"},"language":"en","primary_location":{"id":"doi:10.1007/s00521-023-08882-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00521-023-08882-6","pdf_url":null,"source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"Neural Computing and Applications","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/A5040352780","display_name":"Jingyu Cao","orcid":"https://orcid.org/0000-0003-0508-1279"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingyu Cao","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, 518055, China","School of Automation, Southeast University, Nanjing, 210096, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, 518055, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, 210096, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088413924","display_name":"Lu Dong","orcid":"https://orcid.org/0000-0001-6737-1381"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lu Dong","raw_affiliation_strings":["School of Cyber Science and Engineering, Southeast University, Nanjing, 211189, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Cyber Science and Engineering, Southeast University, Nanjing, 211189, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034047775","display_name":"Xin Yuan","orcid":"https://orcid.org/0000-0002-7472-340X"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Yuan","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, 210096, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, 210096, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076608243","display_name":"Yuanda Wang","orcid":"https://orcid.org/0000-0001-8002-8131"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanda Wang","raw_affiliation_strings":["School of Automation, Southeast University, Nanjing, 210096, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, 210096, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019248683","display_name":"Changyin Sun","orcid":"https://orcid.org/0000-0001-9269-334X"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Changyin Sun","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, 518055, China","School of Automation, Southeast University, Nanjing, 210096, China"],"raw_orcid":"https://orcid.org/0000-0001-9269-334X","affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, 518055, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"School of Automation, Southeast University, Nanjing, 210096, China","institution_ids":["https://openalex.org/I76569877"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019248683"],"corresponding_institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I76569877"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":null,"fwci":1.05,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81453649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"36","issue":"1","first_page":"273","last_page":"287"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9955999851226807,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9815999865531921,"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":0.9284261465072632},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8243393301963806},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5551869869232178},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4889439642429352},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.486234575510025},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44928693771362305},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.43442219495773315},{"id":"https://openalex.org/keywords/computational-science-and-engineering","display_name":"Computational Science and Engineering","score":0.43298354744911194},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3144245743751526},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07598376274108887}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9284261465072632},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8243393301963806},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5551869869232178},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4889439642429352},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.486234575510025},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44928693771362305},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.43442219495773315},{"id":"https://openalex.org/C68597687","wikidata":"https://www.wikidata.org/wiki/Q362601","display_name":"Computational Science and Engineering","level":2,"score":0.43298354744911194},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3144245743751526},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07598376274108887},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00521-023-08882-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s00521-023-08882-6","pdf_url":null,"source":{"id":"https://openalex.org/S147897268","display_name":"Neural Computing and Applications","issn_l":"0941-0643","issn":["0941-0643","1433-3058"],"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":"Neural Computing and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1654982242","display_name":null,"funder_award_id":"U1713209","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5033343354","display_name":null,"funder_award_id":"61921004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6287495588","display_name":null,"funder_award_id":"BK20210215","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G7395770648","display_name":null,"funder_award_id":"62103104","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G800914696","display_name":null,"funder_award_id":"62136008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8877631286","display_name":null,"funder_award_id":"62173251","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/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1498436455","https://openalex.org/W1641379095","https://openalex.org/W2064675550","https://openalex.org/W2768629321","https://openalex.org/W2791797404","https://openalex.org/W2810957722","https://openalex.org/W2915117209","https://openalex.org/W2954111275","https://openalex.org/W2963523627","https://openalex.org/W2963761387","https://openalex.org/W2964227312","https://openalex.org/W2964505566","https://openalex.org/W2998279575","https://openalex.org/W3035829937","https://openalex.org/W3036329728","https://openalex.org/W3037533914","https://openalex.org/W3084268808","https://openalex.org/W3092429416","https://openalex.org/W3134939669","https://openalex.org/W3174733757","https://openalex.org/W3201993717","https://openalex.org/W3205322933","https://openalex.org/W3208890675","https://openalex.org/W4205746880","https://openalex.org/W4225884757","https://openalex.org/W4280646265","https://openalex.org/W4296193205","https://openalex.org/W4303427392","https://openalex.org/W4308361232","https://openalex.org/W6835070974"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W1914583973","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W3088331655","https://openalex.org/W1504584981","https://openalex.org/W3038962357"],"abstract_inverted_index":null,"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":4}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}