{"id":"https://openalex.org/W1980633046","doi":"https://doi.org/10.1109/adprl.2014.7010612","title":"Convergent reinforcement learning control with neural networks and continuous action search","display_name":"Convergent reinforcement learning control with neural networks and continuous action search","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W1980633046","doi":"https://doi.org/10.1109/adprl.2014.7010612","mag":"1980633046"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","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/A5100359267","display_name":"Minwoo Lee","orcid":"https://orcid.org/0000-0002-4939-2936"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Minwoo Lee","raw_affiliation_strings":["Department of Computer Science, Colorado State University, Fort Collins, CO, USA","Dept. of Computer Science, Colorado State University, Fort Collins, CO 80523, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Colorado State University, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I92446798"]},{"raw_affiliation_string":"Dept. of Computer Science, Colorado State University, Fort Collins, CO 80523, USA#TAB#","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036335957","display_name":"Charles W. Anderson","orcid":"https://orcid.org/0000-0001-7392-3840"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles W. Anderson","raw_affiliation_strings":["Department of Computer Science, Colorado State University, Fort Collins, CO, USA","Dept. of Computer Science, Colorado State University, Fort Collins, CO 80523, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Colorado State University, Fort Collins, CO, USA","institution_ids":["https://openalex.org/I92446798"]},{"raw_affiliation_string":"Dept. of Computer Science, Colorado State University, Fort Collins, CO 80523, USA#TAB#","institution_ids":["https://openalex.org/I92446798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100359267"],"corresponding_institution_ids":["https://openalex.org/I92446798"],"apc_list":null,"apc_paid":null,"fwci":2.0451,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.88762956,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9937999844551086,"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":0.7048887014389038},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.582485020160675},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.5559443235397339},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5493872761726379},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5456079840660095},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.49915146827697754},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4924844205379486},{"id":"https://openalex.org/keywords/backpropagation","display_name":"Backpropagation","score":0.4862919747829437},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.47615787386894226},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46490561962127686},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3882730007171631},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30411937832832336},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28010863065719604},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23478132486343384}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7048887014389038},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.582485020160675},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.5559443235397339},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5493872761726379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5456079840660095},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.49915146827697754},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4924844205379486},{"id":"https://openalex.org/C155032097","wikidata":"https://www.wikidata.org/wiki/Q798503","display_name":"Backpropagation","level":3,"score":0.4862919747829437},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.47615787386894226},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46490561962127686},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3882730007171631},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30411937832832336},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28010863065719604},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23478132486343384},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2014.7010612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010612","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W13294968","https://openalex.org/W1531900088","https://openalex.org/W1575327902","https://openalex.org/W1646707810","https://openalex.org/W1994923984","https://openalex.org/W2011562875","https://openalex.org/W2051812123","https://openalex.org/W2065356613","https://openalex.org/W2067243719","https://openalex.org/W2075268401","https://openalex.org/W2101539915","https://openalex.org/W2104641222","https://openalex.org/W2109102709","https://openalex.org/W2121863487","https://openalex.org/W2134042548","https://openalex.org/W2139418546","https://openalex.org/W2141559645","https://openalex.org/W2151613683","https://openalex.org/W2154549708","https://openalex.org/W2155791599","https://openalex.org/W2159008857","https://openalex.org/W2473364827","https://openalex.org/W2953334758","https://openalex.org/W3035712376","https://openalex.org/W4214717370","https://openalex.org/W6600556750","https://openalex.org/W6683001934","https://openalex.org/W6683164292","https://openalex.org/W6683354640"],"related_works":["https://openalex.org/W4387497383","https://openalex.org/W3183948672","https://openalex.org/W3173606202","https://openalex.org/W3110381201","https://openalex.org/W2948807893","https://openalex.org/W2935909890","https://openalex.org/W2778153218","https://openalex.org/W2758277628","https://openalex.org/W1531601525","https://openalex.org/W2381411913"],"abstract_inverted_index":{"We":[0,27],"combine":[1],"a":[2],"convergent":[3,36],"TD-learning":[4],"method":[5],"and":[6,21,54,71,87,96],"direct":[7],"continuous":[8,39,52,89],"action":[9,40,55,90],"search":[10,41,91],"with":[11,42,83],"neural":[12,33],"networks":[13,34],"for":[14,35],"function":[15],"approximation":[16],"to":[17,31,45,62,81,93],"obtain":[18],"both":[19],"stability":[20],"generalization":[22],"over":[23],"inexperienced":[24],"state-action":[25],"pairs.":[26],"extend":[28],"linear":[29,69],"Greedy-GQ":[30,85],"nonlinear":[32,72,84],"learning.":[37],"Direct":[38],"back-propagation":[43],"leads":[44],"efficient":[46],"high-precision":[47],"control.":[48],"A":[49],"high":[50],"dimensional":[51],"state":[53],"problem,":[56],"octopus":[57],"arm":[58],"control,":[59],"is":[60],"examined":[61],"test":[63],"the":[64,77],"proposed":[65],"algorithm.":[66],"Comparing":[67],"TD,":[68],"Greedy-GQ,":[70,73],"we":[74],"discuss":[75],"how":[76,88],"correction":[78],"term":[79],"contributes":[80,92],"learning":[82,94],"algorithm":[86],"speed":[95],"stability.":[97]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}