{"id":"https://openalex.org/W2791641339","doi":"https://doi.org/10.1007/s11704-017-6222-6","title":"Efficient reinforcement learning in continuous state and action spaces with Dyna and policy approximation","display_name":"Efficient reinforcement learning in continuous state and action spaces with Dyna and policy approximation","publication_year":2018,"publication_date":"2018-02-13","ids":{"openalex":"https://openalex.org/W2791641339","doi":"https://doi.org/10.1007/s11704-017-6222-6","mag":"2791641339"},"language":"en","primary_location":{"id":"doi:10.1007/s11704-017-6222-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11704-017-6222-6","pdf_url":null,"source":{"id":"https://openalex.org/S4210231404","display_name":"Frontiers of Computer Science","issn_l":"2095-2228","issn":["2095-2228","2095-2236"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311889","host_organization_name":"Higher Education Press","host_organization_lineage":["https://openalex.org/P4310311889"],"host_organization_lineage_names":["Higher Education Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Computer Science","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/A5101902909","display_name":"Shan Zhong","orcid":"https://orcid.org/0000-0003-0034-6952"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I21741975","display_name":"Suzhou University of Technology","ror":"https://ror.org/05g6ben79","country_code":"CN","type":"education","lineage":["https://openalex.org/I21741975"]},{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]},{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shan Zhong","raw_affiliation_strings":["Jiangsu Province Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, 215006, China","Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China","School of Computer Science and Engineering, Changshu Institute of Technology, Changshu, 215500, China","School of Computer Science and Technology, Soochow University, Suzhou, 215000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Jiangsu Province Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, 215006, China","institution_ids":["https://openalex.org/I308837"]},{"raw_affiliation_string":"Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China","institution_ids":["https://openalex.org/I194450716"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Changshu Institute of Technology, Changshu, 215500, China","institution_ids":["https://openalex.org/I21741975"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, 215000, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100414574","display_name":"Quan Liu","orcid":"https://orcid.org/0000-0002-8710-1810"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Quan Liu","raw_affiliation_strings":["Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing, 210000, China","Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China","School of Computer Science and Technology, Soochow University, Suzhou, 215000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Collaborative Innovation Center of Novel Software Technology and Industrialization, Nanjing, 210000, China","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China","institution_ids":["https://openalex.org/I194450716"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, 215000, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035138959","display_name":"Zongzhang Zhang","orcid":"https://orcid.org/0000-0002-9238-4747"},"institutions":[{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongzhang Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Soochow University, Suzhou, 215000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, 215000, China","institution_ids":["https://openalex.org/I3923682"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101997111","display_name":"Qiming Fu","orcid":"https://orcid.org/0000-0002-8720-9071"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]},{"id":"https://openalex.org/I308837","display_name":"Suzhou University of Science and Technology","ror":"https://ror.org/04en8wb91","country_code":"CN","type":"education","lineage":["https://openalex.org/I308837"]},{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiming Fu","raw_affiliation_strings":["College of Electronic & Information Engineering, Suzhou University of Science and Technology, Suzhou, 215000, China","Jiangsu Province Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, 215006, China","Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China","School of Computer Science and Technology, Soochow University, Suzhou, 215000, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Electronic & Information Engineering, Suzhou University of Science and Technology, Suzhou, 215000, China","institution_ids":["https://openalex.org/I308837"]},{"raw_affiliation_string":"Jiangsu Province Key Laboratory of Intelligent Building Energy Efficiency, Suzhou University of Science and Technology, Suzhou, 215006, China","institution_ids":["https://openalex.org/I308837"]},{"raw_affiliation_string":"Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, Jilin University, Changchun, 130012, China","institution_ids":["https://openalex.org/I194450716"]},{"raw_affiliation_string":"School of Computer Science and Technology, Soochow University, Suzhou, 215000, China","institution_ids":["https://openalex.org/I3923682"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100414574"],"corresponding_institution_ids":["https://openalex.org/I194450716","https://openalex.org/I3923682"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":null,"fwci":1.8018,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.88390149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"13","issue":"1","first_page":"106","last_page":"126"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9994000196456909,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9782999753952026,"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":0.8176774382591248},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7078672051429749},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6458448767662048},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4921204447746277},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4636119306087494},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.460365891456604},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4598378539085388},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44445502758026123},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.441377192735672},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22030508518218994},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20246565341949463},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.19164451956748962},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07632207870483398}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8176774382591248},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7078672051429749},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6458448767662048},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4921204447746277},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4636119306087494},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.460365891456604},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4598378539085388},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44445502758026123},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.441377192735672},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22030508518218994},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20246565341949463},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.19164451956748962},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07632207870483398},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","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},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11704-017-6222-6","is_oa":false,"landing_page_url":"https://doi.org/10.1007/s11704-017-6222-6","pdf_url":null,"source":{"id":"https://openalex.org/S4210231404","display_name":"Frontiers of Computer Science","issn_l":"2095-2228","issn":["2095-2228","2095-2236"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310311889","host_organization_name":"Higher Education Press","host_organization_lineage":["https://openalex.org/P4310311889"],"host_organization_lineage_names":["Higher Education Press"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers of Computer Science","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":72,"referenced_works":["https://openalex.org/W75509695","https://openalex.org/W86816279","https://openalex.org/W137325057","https://openalex.org/W146900863","https://openalex.org/W178169250","https://openalex.org/W755046805","https://openalex.org/W1491843047","https://openalex.org/W1507222174","https://openalex.org/W1511421254","https://openalex.org/W1535210759","https://openalex.org/W1540723801","https://openalex.org/W1583837637","https://openalex.org/W1589747210","https://openalex.org/W1626155273","https://openalex.org/W1714211023","https://openalex.org/W1758031947","https://openalex.org/W1778554682","https://openalex.org/W1881819129","https://openalex.org/W1966086707","https://openalex.org/W1985093013","https://openalex.org/W2006330826","https://openalex.org/W2024390895","https://openalex.org/W2048226872","https://openalex.org/W2048687352","https://openalex.org/W2062533874","https://openalex.org/W2072931156","https://openalex.org/W2077671246","https://openalex.org/W2093831009","https://openalex.org/W2094387729","https://openalex.org/W2112264645","https://openalex.org/W2112483970","https://openalex.org/W2118556122","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2125191551","https://openalex.org/W2130599357","https://openalex.org/W2131030156","https://openalex.org/W2132301339","https://openalex.org/W2132351269","https://openalex.org/W2134882417","https://openalex.org/W2139418546","https://openalex.org/W2145339207","https://openalex.org/W2153039919","https://openalex.org/W2158316397","https://openalex.org/W2159543578","https://openalex.org/W2160284799","https://openalex.org/W2160561608","https://openalex.org/W2161632769","https://openalex.org/W2177967097","https://openalex.org/W2188892596","https://openalex.org/W2232866954","https://openalex.org/W2249513906","https://openalex.org/W2249840556","https://openalex.org/W2399790246","https://openalex.org/W2401533533","https://openalex.org/W2531875963","https://openalex.org/W2532646799","https://openalex.org/W2536379393","https://openalex.org/W2559997609","https://openalex.org/W2602753196","https://openalex.org/W2606126444","https://openalex.org/W2614653677","https://openalex.org/W2739602616","https://openalex.org/W2804945724","https://openalex.org/W2912100673","https://openalex.org/W2949317487","https://openalex.org/W2949510529","https://openalex.org/W4214717370","https://openalex.org/W4230846739","https://openalex.org/W4240285010","https://openalex.org/W4292403327","https://openalex.org/W4298336071"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894","https://openalex.org/W2386410636","https://openalex.org/W3038962357"],"abstract_inverted_index":null,"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-19T15:47:20.252518","created_date":"2025-10-10T00:00:00"}
