{"id":"https://openalex.org/W1511927616","doi":"https://doi.org/10.1007/978-3-642-04020-7_30","title":"Using Control Theory for Analysis of Reinforcement Learning and Optimal Policy Properties in Grid-World Problems","display_name":"Using Control Theory for Analysis of Reinforcement Learning and Optimal Policy Properties in Grid-World Problems","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W1511927616","doi":"https://doi.org/10.1007/978-3-642-04020-7_30","mag":"1511927616"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-642-04020-7_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-04020-7_30","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","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/A5076995864","display_name":"S. Mostapha Kalami Heris","orcid":"https://orcid.org/0000-0002-2425-3796"},"institutions":[{"id":"https://openalex.org/I80543232","display_name":"K.N.Toosi University of Technology","ror":"https://ror.org/0433abe34","country_code":"IR","type":"education","lineage":["https://openalex.org/I80543232"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"S. Mostapha Kalami Heris","raw_affiliation_strings":["Control Engineering Department, Faculty of Electrical Engineering, K. N. Toosi University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Control Engineering Department, Faculty of Electrical Engineering, K. N. Toosi University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I80543232"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037986038","display_name":"Mohammad Bagher Naghibi Sistani","orcid":"https://orcid.org/0000-0003-1414-8199"},"institutions":[{"id":"https://openalex.org/I86958956","display_name":"Ferdowsi University of Mashhad","ror":"https://ror.org/00g6ka752","country_code":"IR","type":"education","lineage":["https://openalex.org/I86958956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammad-Bagher Naghibi Sistani","raw_affiliation_strings":["Electrical Engineering Department, Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran","institution_ids":["https://openalex.org/I86958956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056660688","display_name":"Naser Pariz","orcid":"https://orcid.org/0000-0001-6689-9176"},"institutions":[{"id":"https://openalex.org/I86958956","display_name":"Ferdowsi University of Mashhad","ror":"https://ror.org/00g6ka752","country_code":"IR","type":"education","lineage":["https://openalex.org/I86958956"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Naser Pariz","raw_affiliation_strings":["Electrical Engineering Department, Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering Department, Faculty of Engineering, Ferdowsi University of Mashhad, Mashhad, Iran","institution_ids":["https://openalex.org/I86958956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076995864"],"corresponding_institution_ids":["https://openalex.org/I80543232"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.09044063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9948999881744385,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9061558246612549},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8463188409805298},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7678121328353882},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6544462442398071},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.6349397301673889},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5977656245231628},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5278537273406982},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.5226250290870667},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4370633661746979},{"id":"https://openalex.org/keywords/optimal-control","display_name":"Optimal control","score":0.4368015229701996},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4126773774623871},{"id":"https://openalex.org/keywords/stochastic-control","display_name":"Stochastic control","score":0.4108622372150421},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.21082231402397156},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2065027952194214},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1600073277950287},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.11901217699050903}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.9061558246612549},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8463188409805298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7678121328353882},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6544462442398071},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.6349397301673889},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5977656245231628},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5278537273406982},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5226250290870667},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4370633661746979},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4368015229701996},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4126773774623871},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.4108622372150421},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.21082231402397156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2065027952194214},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1600073277950287},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11901217699050903},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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":2,"locations":[{"id":"doi:10.1007/978-3-642-04020-7_30","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-642-04020-7_30","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:shura.shu.ac.uk:34902","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401600","display_name":"SHURA (Sheffield Hallam University Research Archive) (Sheffield Hallam University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I71422933","host_organization_name":"Sheffield Hallam University","host_organization_lineage":["https://openalex.org/I71422933"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"PeerReviewed"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.75,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W63429079","https://openalex.org/W64796606","https://openalex.org/W92265916","https://openalex.org/W104447620","https://openalex.org/W149039294","https://openalex.org/W180325379","https://openalex.org/W202271766","https://openalex.org/W573181897","https://openalex.org/W1481834144","https://openalex.org/W1506832649","https://openalex.org/W1515851193","https://openalex.org/W1516418405","https://openalex.org/W1549519846","https://openalex.org/W1552300625","https://openalex.org/W1554120378","https://openalex.org/W1576452626","https://openalex.org/W1577199596","https://openalex.org/W1583072328","https://openalex.org/W1584456573","https://openalex.org/W1854776945","https://openalex.org/W1965662014","https://openalex.org/W1988217924","https://openalex.org/W1998148366","https://openalex.org/W2082607057","https://openalex.org/W2100857832","https://openalex.org/W2107726111","https://openalex.org/W2109393574","https://openalex.org/W2119567691","https://openalex.org/W2121863487","https://openalex.org/W2128467312","https://openalex.org/W2129981463","https://openalex.org/W4214717370"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W2364406457","https://openalex.org/W2173087131","https://openalex.org/W1997350370","https://openalex.org/W1574958246"],"abstract_inverted_index":null,"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
