{"id":"https://openalex.org/W2964300187","doi":"https://doi.org/10.1007/978-3-030-26354-6_1","title":"Multi-robot Cooperation Strategy in a Partially Observable Markov Game Using Enhanced Deep Deterministic Policy Gradient","display_name":"Multi-robot Cooperation Strategy in a Partially Observable Markov Game Using Enhanced Deep Deterministic Policy Gradient","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W2964300187","doi":"https://doi.org/10.1007/978-3-030-26354-6_1","mag":"2964300187"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-26354-6_1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-26354-6_1","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","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/A5006334165","display_name":"Qirong Tang","orcid":"https://orcid.org/0000-0002-5541-4660"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qirong Tang","raw_affiliation_strings":["Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, No. 4800, Cao An Rd., Shanghai, 201804, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, No. 4800, Cao An Rd., Shanghai, 201804, People\u2019s Republic of China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100734992","display_name":"Jingtao Zhang","orcid":"https://orcid.org/0000-0003-3690-3968"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingtao Zhang","raw_affiliation_strings":["Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, No. 4800, Cao An Rd., Shanghai, 201804, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, No. 4800, Cao An Rd., Shanghai, 201804, People\u2019s Republic of China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041393155","display_name":"Fangchao Yu","orcid":"https://orcid.org/0000-0003-0889-3790"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangchao Yu","raw_affiliation_strings":["Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, No. 4800, Cao An Rd., Shanghai, 201804, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, No. 4800, Cao An Rd., Shanghai, 201804, People\u2019s Republic of China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050762764","display_name":"Pengjie Xu","orcid":"https://orcid.org/0009-0005-6114-9145"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pengjie Xu","raw_affiliation_strings":["Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, No. 4800, Cao An Rd., Shanghai, 201804, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, No. 4800, Cao An Rd., Shanghai, 201804, People\u2019s Republic of China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034357624","display_name":"Zhongqun Zhang","orcid":"https://orcid.org/0000-0003-0884-8711"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongqun Zhang","raw_affiliation_strings":["Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, No. 4800, Cao An Rd., Shanghai, 201804, People\u2019s Republic of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Robotics and Multibody System, School of Mechanical Engineering, Tongji University, No. 4800, Cao An Rd., Shanghai, 201804, People\u2019s Republic of China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5006334165"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.1093,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.38229034,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998999834060669,"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":0.9998999834060669,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9825999736785889,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9800000190734863,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7467775344848633},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7435287833213806},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.7413206100463867},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6389074325561523},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5538166165351868},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.530551016330719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5214178562164307},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5015959739685059},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.49389296770095825},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4718867540359497},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4422438442707062},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.36523181200027466},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.276188462972641},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1871318221092224},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18639802932739258},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0895794928073883}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7467775344848633},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7435287833213806},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.7413206100463867},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6389074325561523},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5538166165351868},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.530551016330719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5214178562164307},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5015959739685059},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.49389296770095825},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4718867540359497},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4422438442707062},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.36523181200027466},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.276188462972641},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1871318221092224},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18639802932739258},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0895794928073883},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-26354-6_1","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-26354-6_1","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"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":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1641379095","https://openalex.org/W2035057654","https://openalex.org/W2096145798","https://openalex.org/W2165150801","https://openalex.org/W2372575675","https://openalex.org/W2395575420","https://openalex.org/W2560105324","https://openalex.org/W2611940445","https://openalex.org/W2726275180","https://openalex.org/W2768629321","https://openalex.org/W2807781934","https://openalex.org/W2887439418","https://openalex.org/W2949201811","https://openalex.org/W2964161785"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W3096874164","https://openalex.org/W1589140671","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W2937181779"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}