{"id":"https://openalex.org/W2105442158","doi":"https://doi.org/10.1109/ijcnn.2004.1380086","title":"Model-free off-policy reinforcement learning in continuous environment","display_name":"Model-free off-policy reinforcement learning in continuous environment","publication_year":2005,"publication_date":"2005-04-05","ids":{"openalex":"https://openalex.org/W2105442158","doi":"https://doi.org/10.1109/ijcnn.2004.1380086","mag":"2105442158"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2004.1380086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","raw_type":"proceedings-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/A5056517464","display_name":"Pawe\u0142 Wawrzy\u0144ski","orcid":"https://orcid.org/0000-0002-1154-0470"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"P. Wawrzynski","raw_affiliation_strings":["Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, Poland","Inst. of Control & Comput. Eng, Warsaw Univ. of Technol., Poland"],"affiliations":[{"raw_affiliation_string":"Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, Poland","institution_ids":["https://openalex.org/I108403487"]},{"raw_affiliation_string":"Inst. of Control & Comput. Eng, Warsaw Univ. of Technol., Poland","institution_ids":["https://openalex.org/I108403487"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052747358","display_name":"Andrzej Pacut","orcid":"https://orcid.org/0000-0003-3489-8990"},"institutions":[{"id":"https://openalex.org/I108403487","display_name":"Warsaw University of Technology","ror":"https://ror.org/00y0xnp53","country_code":"PL","type":"education","lineage":["https://openalex.org/I108403487"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"A. Pacut","raw_affiliation_strings":["Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, Poland","Inst. of Control & Comput. Eng, Warsaw Univ. of Technol., Poland"],"affiliations":[{"raw_affiliation_string":"Institute of Control and Computation Engineering, Warsaw University of Technology, Warsaw, Poland","institution_ids":["https://openalex.org/I108403487"]},{"raw_affiliation_string":"Inst. of Control & Comput. Eng, Warsaw Univ. of Technol., Poland","institution_ids":["https://openalex.org/I108403487"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5056517464"],"corresponding_institution_ids":["https://openalex.org/I108403487"],"apc_list":null,"apc_paid":null,"fwci":0.4567,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.75301717,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"1091","last_page":"1096"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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":0.9990000128746033,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9879999756813049,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9714000225067139,"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":0.8962250351905823},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7313548922538757},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.718694269657135},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5643233060836792},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5204553604125977},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5046724081039429},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.45810604095458984},{"id":"https://openalex.org/keywords/temporal-difference-learning","display_name":"Temporal difference learning","score":0.4523804783821106},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4377460479736328},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4353013038635254},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33573275804519653},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.32161229848861694},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13700583577156067},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13155579566955566}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8962250351905823},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7313548922538757},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718694269657135},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5643233060836792},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5204553604125977},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5046724081039429},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.45810604095458984},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.4523804783821106},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4377460479736328},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4353013038635254},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33573275804519653},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32161229848861694},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13700583577156067},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13155579566955566},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ijcnn.2004.1380086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2004.1380086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.60.9263","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.60.9263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://staff.elka.pw.edu.pl/~pwawrzyn/pub-s/0401_IRPO.ps","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5199999809265137,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W80219033","https://openalex.org/W1491843047","https://openalex.org/W1514587017","https://openalex.org/W1600046456","https://openalex.org/W1600680420","https://openalex.org/W2009303086","https://openalex.org/W2048226872","https://openalex.org/W2091565802","https://openalex.org/W2099833070","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2147632348","https://openalex.org/W2155027007","https://openalex.org/W2156737235","https://openalex.org/W2396474512","https://openalex.org/W4214717370","https://openalex.org/W4233358567","https://openalex.org/W4245108548","https://openalex.org/W6630907848","https://openalex.org/W6635798015","https://openalex.org/W6675086535","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W2145363145","https://openalex.org/W2341346307","https://openalex.org/W2154399718","https://openalex.org/W4321463377","https://openalex.org/W2768629321","https://openalex.org/W2130711276","https://openalex.org/W4308828368","https://openalex.org/W1528400370","https://openalex.org/W2152445738","https://openalex.org/W3038962357"],"abstract_inverted_index":{"We":[0,74],"introduce":[1],"an":[2,35],"algorithm":[3,21,77,85],"of":[4,26,34,47,68,71,100],"reinforcement":[5,53],"learning":[6,54],"in":[7,51,78,91],"continuous":[8],"state":[9],"and":[10],"action":[11],"spaces.":[12],"In":[13],"order":[14],"to":[15,87,97],"construct":[16],"a":[17,32,69],"control":[18,88],"policy,":[19],"the":[20,23,45,61,72,79,110],"utilizes":[22],"entire":[24],"history":[25,62],"agent-environment":[27],"interaction.":[28],"The":[29,56,84],"policy":[30,57],"is":[31,58,105],"result":[33,46],"estimation":[36],"process":[37],"based":[38],"on":[39],"all":[40],"available":[41],"information":[42],"rather":[43],"than":[44,109],"stochastic":[48],"convergence":[49],"as":[50],"classical":[52],"approaches.":[55],"derived":[59],"from":[60],"directly,":[63],"not":[64],"through":[65],"any":[66],"kind":[67],"model":[70],"environment.":[73,83],"test":[75],"our":[76],"cart-pole":[80],"swing-up":[81],"simulated":[82],"learns":[86],"this":[89],"plant":[90],"about":[92],"100":[93],"trials,":[94],"which":[95],"corresponds":[96],"15":[98],"minutes":[99],"plant's":[101],"real":[102],"time.":[103],"This":[104],"several":[106],"times":[107],"shorter":[108],"one":[111],"required":[112],"by":[113],"other":[114],"algorithms.":[115]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}