{"id":"https://openalex.org/W1535225803","doi":"https://doi.org/10.1007/978-0-85729-130-1_13","title":"On Reinforcement Memory for Non-Markovian Control","display_name":"On Reinforcement Memory for Non-Markovian Control","publication_year":2010,"publication_date":"2010-10-29","ids":{"openalex":"https://openalex.org/W1535225803","doi":"https://doi.org/10.1007/978-0-85729-130-1_13","mag":"1535225803"},"language":"en","primary_location":{"id":"doi:10.1007/978-0-85729-130-1_13","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-0-85729-130-1_13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Research and Development in Intelligent Systems XXVII","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/A5003210928","display_name":"Hassab Elgawi Osman","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Hassab Elgawi Osman","raw_affiliation_strings":["The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5003210928"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1663183,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"179","last_page":"192"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9882000088691711,"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/T10320","display_name":"Neural Networks and Applications","score":0.9868000149726868,"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":0.8227818608283997},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6530132293701172},{"id":"https://openalex.org/keywords/controller","display_name":"Controller (irrigation)","score":0.6031036972999573},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.569658637046814},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5513326525688171},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.4841804802417755},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.4295884966850281},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4252839982509613},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4131420850753784},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3766329884529114},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.32120275497436523},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.19291606545448303},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.12439662218093872},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12269729375839233}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8227818608283997},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6530132293701172},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6031036972999573},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.569658637046814},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5513326525688171},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4841804802417755},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.4295884966850281},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4252839982509613},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4131420850753784},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3766329884529114},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.32120275497436523},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19291606545448303},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.12439662218093872},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12269729375839233},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems 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/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/978-0-85729-130-1_13","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-0-85729-130-1_13","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Research and Development in Intelligent Systems XXVII","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W80465719","https://openalex.org/W205747712","https://openalex.org/W1488897928","https://openalex.org/W1557073320","https://openalex.org/W1607052939","https://openalex.org/W1640774615","https://openalex.org/W1657542410","https://openalex.org/W1657674574","https://openalex.org/W2011233848","https://openalex.org/W2045491133","https://openalex.org/W2047868442","https://openalex.org/W2073782853","https://openalex.org/W2076329865","https://openalex.org/W2092726287","https://openalex.org/W2099873296","https://openalex.org/W2100787464","https://openalex.org/W2118065494","https://openalex.org/W2121863487","https://openalex.org/W2125200267","https://openalex.org/W2144935315","https://openalex.org/W2153562927","https://openalex.org/W2154549708","https://openalex.org/W2155027007","https://openalex.org/W2168359464","https://openalex.org/W2169982856","https://openalex.org/W2535652371","https://openalex.org/W3147501999","https://openalex.org/W4214717370","https://openalex.org/W4253841143","https://openalex.org/W6637000695","https://openalex.org/W6677916085","https://openalex.org/W6680962578","https://openalex.org/W6682813660"],"related_works":["https://openalex.org/W3096874164","https://openalex.org/W2937181779","https://openalex.org/W1985560493","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W4284974072","https://openalex.org/W2341346307","https://openalex.org/W4225269853","https://openalex.org/W2386410636"],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}