{"id":"https://openalex.org/W2037488749","doi":"https://doi.org/10.1109/adprl.2014.7010614","title":"Theoretical analysis of a reinforcement learning based switching scheme","display_name":"Theoretical analysis of a reinforcement learning based switching scheme","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2037488749","doi":"https://doi.org/10.1109/adprl.2014.7010614","mag":"2037488749"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2014.7010614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010614","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/A5101547396","display_name":"Ali Heydari","orcid":"https://orcid.org/0000-0002-1569-8240"},"institutions":[{"id":"https://openalex.org/I184647316","display_name":"South Dakota School of Mines and Technology","ror":"https://ror.org/00ch7yk27","country_code":"US","type":"education","lineage":["https://openalex.org/I184647316"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ali Heydari","raw_affiliation_strings":["Mechanical Engineering Department, South Dakota School of Mines and Technology, Rapid City, SD","Mechanical Engineering Department, South Dakota School of Mines and Technology, Rapid City SD 57701"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering Department, South Dakota School of Mines and Technology, Rapid City, SD","institution_ids":["https://openalex.org/I184647316"]},{"raw_affiliation_string":"Mechanical Engineering Department, South Dakota School of Mines and Technology, Rapid City SD 57701","institution_ids":["https://openalex.org/I184647316"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5101547396"],"corresponding_institution_ids":["https://openalex.org/I184647316"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1013801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998000264167786,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9977999925613403,"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/T10249","display_name":"Distributed Control Multi-Agent Systems","score":0.9388999938964844,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8163390159606934},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7948943376541138},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.7200838327407837},{"id":"https://openalex.org/keywords/limit","display_name":"Limit (mathematics)","score":0.707076907157898},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6314291954040527},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5938901305198669},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5914962887763977},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5876256227493286},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.453732430934906},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3554997444152832},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.3338235914707184},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21872588992118835}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8163390159606934},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7948943376541138},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.7200838327407837},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.707076907157898},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6314291954040527},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5938901305198669},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5914962887763977},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5876256227493286},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.453732430934906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3554997444152832},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.3338235914707184},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21872588992118835},{"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"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:10.1109/adprl.2014.7010614","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2014.7010614","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1510124874","https://openalex.org/W1546772360","https://openalex.org/W1574514837","https://openalex.org/W1584101032","https://openalex.org/W1999743136","https://openalex.org/W2000975219","https://openalex.org/W2002007892","https://openalex.org/W2003225665","https://openalex.org/W2013184330","https://openalex.org/W2034679997","https://openalex.org/W2038341035","https://openalex.org/W2060578001","https://openalex.org/W2061280864","https://openalex.org/W2093831009","https://openalex.org/W2098035803","https://openalex.org/W2114424860","https://openalex.org/W2116090176","https://openalex.org/W2118819183","https://openalex.org/W2129422716","https://openalex.org/W2132858840","https://openalex.org/W2136064843","https://openalex.org/W2137983211","https://openalex.org/W2138131694","https://openalex.org/W2158625202","https://openalex.org/W2171880613","https://openalex.org/W2172254357","https://openalex.org/W2342673534","https://openalex.org/W2478309693","https://openalex.org/W2595897327","https://openalex.org/W3150488336","https://openalex.org/W3213472335","https://openalex.org/W4214717370","https://openalex.org/W6632601854","https://openalex.org/W6650216790","https://openalex.org/W6679167579","https://openalex.org/W6704013665","https://openalex.org/W6804409665"],"related_works":["https://openalex.org/W4362501864","https://openalex.org/W4306904969","https://openalex.org/W4380318855","https://openalex.org/W2138720691","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W3049728571","https://openalex.org/W20361778","https://openalex.org/W2024136090","https://openalex.org/W2361975388"],"abstract_inverted_index":{"A":[0],"reinforcement":[1],"learning":[2],"based":[3],"scheme":[4],"for":[5,57,63],"optimal":[6],"switching":[7],"with":[8],"an":[9],"infinite-horizon":[10],"cost":[11],"function":[12,45],"is":[13,53],"briefly":[14],"proposed":[15],"in":[16],"this":[17],"paper.":[18],"Several":[19],"theoretical":[20],"questions":[21],"are":[22,68],"shown":[23],"to":[24,39],"arise":[25],"regarding":[26],"its":[27],"convergence,":[28,64],"optimality":[29],"of":[30,35,50],"the":[31,36,51,58],"result,":[32],"and":[33,66],"continuity":[34,67],"limit":[37],"function,":[38],"be":[40],"uniformly":[41],"approximated":[42],"using":[43],"parametric":[44],"approximators.":[46],"The":[47],"main":[48],"contribution":[49],"paper":[52],"providing":[54],"rigorous":[55],"answers":[56],"questions,":[59],"where,":[60],"sufficient":[61],"conditions":[62],"optimality,":[65],"provided.":[69]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}