{"id":"https://openalex.org/W3014975158","doi":"https://doi.org/10.1007/978-3-030-44267-5_25","title":"Continuous Control in Deep Reinforcement Learning with Direct Policy Derivation from Q Network","display_name":"Continuous Control in Deep Reinforcement Learning with Direct Policy Derivation from Q Network","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3014975158","doi":"https://doi.org/10.1007/978-3-030-44267-5_25","mag":"3014975158"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-44267-5_25","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-44267-5_25","pdf_url":null,"source":{"id":"https://openalex.org/S2764905038","display_name":"Advances in intelligent systems and computing","issn_l":"2194-5357","issn":["2194-5357","2194-5365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Intelligent Systems and Computing","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/A5063588538","display_name":"Aydar Akhmetzyanov","orcid":"https://orcid.org/0000-0002-0939-4080"},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Aydar Akhmetzyanov","raw_affiliation_strings":["Center for Technologies in Robotics and Mechatronics Components, Innopolis University, Innopolis, Russia"],"affiliations":[{"raw_affiliation_string":"Center for Technologies in Robotics and Mechatronics Components, Innopolis University, Innopolis, Russia","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053337576","display_name":"Rauf Yagfarov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Rauf Yagfarov","raw_affiliation_strings":["Center for Technologies in Robotics and Mechatronics Components, Innopolis University, Innopolis, Russia"],"affiliations":[{"raw_affiliation_string":"Center for Technologies in Robotics and Mechatronics Components, Innopolis University, Innopolis, Russia","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073176480","display_name":"Salimzhan Gafurov","orcid":"https://orcid.org/0000-0002-9414-7235"},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Salimzhan Gafurov","raw_affiliation_strings":["Center for Technologies in Robotics and Mechatronics Components, Innopolis University, Innopolis, Russia"],"affiliations":[{"raw_affiliation_string":"Center for Technologies in Robotics and Mechatronics Components, Innopolis University, Innopolis, Russia","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063745058","display_name":"Mikhail Ostanin","orcid":"https://orcid.org/0000-0003-3145-8818"},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Mikhail Ostanin","raw_affiliation_strings":["Center for Technologies in Robotics and Mechatronics Components, Innopolis University, Innopolis, Russia"],"affiliations":[{"raw_affiliation_string":"Center for Technologies in Robotics and Mechatronics Components, Innopolis University, Innopolis, Russia","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044427900","display_name":"Alexandr Klimchik","orcid":"https://orcid.org/0000-0002-2244-1849"},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Alexandr Klimchik","raw_affiliation_strings":["Center for Technologies in Robotics and Mechatronics Components, Innopolis University, Innopolis, Russia"],"affiliations":[{"raw_affiliation_string":"Center for Technologies in Robotics and Mechatronics Components, Innopolis University, Innopolis, Russia","institution_ids":["https://openalex.org/I4210116741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063588538"],"corresponding_institution_ids":["https://openalex.org/I4210116741"],"apc_list":null,"apc_paid":null,"fwci":1.0989,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.79515741,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"168","last_page":"174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9983999729156494,"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":0.9983999729156494,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9135000109672546,"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":0.8536996841430664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6925217509269714},{"id":"https://openalex.org/keywords/discretization","display_name":"Discretization","score":0.6749711036682129},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6124420762062073},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5425570011138916},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5298683047294617},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5158814191818237},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.47702667117118835},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.42806926369667053},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3755798935890198},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.348901629447937},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.1954808235168457},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19078513979911804}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8536996841430664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6925217509269714},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.6749711036682129},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6124420762062073},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5425570011138916},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5298683047294617},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5158814191818237},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.47702667117118835},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.42806926369667053},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3755798935890198},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.348901629447937},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.1954808235168457},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19078513979911804},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-3-030-44267-5_25","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-44267-5_25","pdf_url":null,"source":{"id":"https://openalex.org/S2764905038","display_name":"Advances in intelligent systems and computing","issn_l":"2194-5357","issn":["2194-5357","2194-5365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319965","host_organization_name":"Springer Nature","host_organization_lineage":["https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Advances in Intelligent Systems and Computing","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4399999976158142,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1557517019","https://openalex.org/W1757796397","https://openalex.org/W2167489871","https://openalex.org/W2173248099","https://openalex.org/W2341171179","https://openalex.org/W2781726626","https://openalex.org/W2787938642","https://openalex.org/W2885163910","https://openalex.org/W2888442053","https://openalex.org/W2899771611","https://openalex.org/W2964043796","https://openalex.org/W6637967152","https://openalex.org/W6756040250","https://openalex.org/W6814003322"],"related_works":["https://openalex.org/W2006251942","https://openalex.org/W2364741597","https://openalex.org/W1492103595","https://openalex.org/W1864774435","https://openalex.org/W946352265","https://openalex.org/W3020787026","https://openalex.org/W2334479858","https://openalex.org/W2799209613","https://openalex.org/W2793786119","https://openalex.org/W1507702947"],"abstract_inverted_index":null,"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}