{"id":"https://openalex.org/W3121607432","doi":"https://doi.org/10.1007/978-3-030-67540-0_20","title":"BiC-DDPG: Bidirectionally-Coordinated Nets for Deep Multi-agent Reinforcement Learning","display_name":"BiC-DDPG: Bidirectionally-Coordinated Nets for Deep Multi-agent Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3121607432","doi":"https://doi.org/10.1007/978-3-030-67540-0_20","mag":"3121607432"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-67540-0_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-67540-0_20","pdf_url":null,"source":{"id":"https://openalex.org/S4393917809","display_name":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","issn_l":"1867-8211","issn":["1867-8211","1867-822X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","raw_type":"book-chapter"},"type":"book-chapter","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/A5031404939","display_name":"Gongju Wang","orcid":"https://orcid.org/0000-0002-7162-3067"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gongju Wang","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019758816","display_name":"Dianxi Shi","orcid":"https://orcid.org/0000-0002-8112-371X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dianxi Shi","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China","Tianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100884245","display_name":"Chao Xue","orcid":"https://orcid.org/0000-0002-9507-9991"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Xue","raw_affiliation_strings":["Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China","Tianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin, China"],"affiliations":[{"raw_affiliation_string":"Artificial Intelligence Research Center (AIRC), National Innovation Institute of Defense Technology (NIIDT), Beijing, China","institution_ids":[]},{"raw_affiliation_string":"Tianjin Artificial Intelligence Innovation Center (TAIIC), Tianjin, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101763478","display_name":"Hao Jiang","orcid":"https://orcid.org/0000-0002-8304-3692"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Jiang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100455413","display_name":"Yajie Wang","orcid":"https://orcid.org/0000-0002-0962-4464"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yajie Wang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5031404939"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.717,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.66762664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"337","last_page":"354"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9969000220298767,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9763000011444092,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8182627558708191},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6187905073165894},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6173914074897766},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6108489036560059},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5584718585014343},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5394511818885803},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4502137303352356},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.42195045948028564},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.41740018129348755},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.28629666566848755},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2509310841560364}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8182627558708191},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6187905073165894},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6173914074897766},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6108489036560059},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5584718585014343},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5394511818885803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4502137303352356},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.42195045948028564},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41740018129348755},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.28629666566848755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2509310841560364},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-67540-0_20","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-67540-0_20","pdf_url":null,"source":{"id":"https://openalex.org/S4393917809","display_name":"Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","issn_l":"1867-8211","issn":["1867-8211","1867-822X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1519783625","https://openalex.org/W1542941925","https://openalex.org/W1714211023","https://openalex.org/W1757796397","https://openalex.org/W1973039793","https://openalex.org/W2049934117","https://openalex.org/W2121863487","https://openalex.org/W2130695501","https://openalex.org/W2131774270","https://openalex.org/W2173248099","https://openalex.org/W2181523240","https://openalex.org/W2215378786","https://openalex.org/W2257979135","https://openalex.org/W2402402867","https://openalex.org/W2617547828","https://openalex.org/W2626637010","https://openalex.org/W2725258047","https://openalex.org/W2749807327","https://openalex.org/W2756196406","https://openalex.org/W2794643322","https://openalex.org/W2903238042","https://openalex.org/W2924523928","https://openalex.org/W2951984055","https://openalex.org/W2963407617","https://openalex.org/W2982316857","https://openalex.org/W6637967152","https://openalex.org/W6758846586"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1626977535","https://openalex.org/W2145363145","https://openalex.org/W4386148312","https://openalex.org/W3213537191","https://openalex.org/W4287868411","https://openalex.org/W3212442854","https://openalex.org/W4362598698","https://openalex.org/W1973039793","https://openalex.org/W1563041104"],"abstract_inverted_index":null,"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}