{"id":"https://openalex.org/W2897554812","doi":"https://doi.org/10.1109/tnnls.2018.2869978","title":"Exploiting Generalization in the Subspaces for Faster Model-Based Reinforcement Learning","display_name":"Exploiting Generalization in the Subspaces for Faster Model-Based Reinforcement Learning","publication_year":2018,"publication_date":"2018-10-10","ids":{"openalex":"https://openalex.org/W2897554812","doi":"https://doi.org/10.1109/tnnls.2018.2869978","mag":"2897554812","pmid":"https://pubmed.ncbi.nlm.nih.gov/30307878"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2018.2869978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2869978","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5050065318","display_name":"Maryam Hashemzadeh","orcid":"https://orcid.org/0000-0002-6357-3311"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Maryam Hashemzadeh","raw_affiliation_strings":["Computational Audio-Vision Laboratory, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, IR, Iran","Cognitive Systems Laboratory, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, IR, Iran"],"raw_orcid":"https://orcid.org/0000-0002-6357-3311","affiliations":[{"raw_affiliation_string":"Computational Audio-Vision Laboratory, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, IR, Iran","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"Cognitive Systems Laboratory, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, IR, Iran","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068354481","display_name":"Reshad Hosseini","orcid":"https://orcid.org/0000-0002-3669-760X"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Reshad Hosseini","raw_affiliation_strings":["Computational Audio-Vision Laboratory, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, IR, Iran","[Computational Audio-Vision Laboratory, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, IR, Iran]"],"raw_orcid":"https://orcid.org/0000-0002-3669-760X","affiliations":[{"raw_affiliation_string":"Computational Audio-Vision Laboratory, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, IR, Iran","institution_ids":["https://openalex.org/I23946033"]},{"raw_affiliation_string":"[Computational Audio-Vision Laboratory, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, IR, Iran]","institution_ids":["https://openalex.org/I23946033"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072135442","display_name":"Majid Nili Ahmadabadi","orcid":"https://orcid.org/0000-0002-6370-6057"},"institutions":[{"id":"https://openalex.org/I23946033","display_name":"University of Tehran","ror":"https://ror.org/05vf56z40","country_code":"IR","type":"education","lineage":["https://openalex.org/I23946033"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Majid Nili Ahmadabadi","raw_affiliation_strings":["Cognitive Systems Laboratory, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, IR, Iran"],"raw_orcid":"https://orcid.org/0000-0002-6370-6057","affiliations":[{"raw_affiliation_string":"Cognitive Systems Laboratory, School of Electrical and Computer Engineering, College of Engineering, University of Tehran, Tehran, IR, Iran","institution_ids":["https://openalex.org/I23946033"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I23946033"],"apc_list":null,"apc_paid":null,"fwci":2.1294,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.9042413,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"30","issue":"6","first_page":"1635","last_page":"1650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9825000166893005,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9776999950408936,"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/linear-subspace","display_name":"Linear subspace","score":0.8991826772689819},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.7471233010292053},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.743596076965332},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6746569871902466},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5377874970436096},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5369387269020081},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4578510522842407},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.44757843017578125},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3768322765827179},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3282063901424408},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07898253202438354}],"concepts":[{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.8991826772689819},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.7471233010292053},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.743596076965332},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6746569871902466},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5377874970436096},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5369387269020081},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4578510522842407},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.44757843017578125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3768322765827179},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3282063901424408},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07898253202438354},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2018.2869978","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2018.2869978","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:30307878","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/30307878","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8500000238418579,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W16011919","https://openalex.org/W21934178","https://openalex.org/W166862392","https://openalex.org/W1491843047","https://openalex.org/W1581202840","https://openalex.org/W1589747210","https://openalex.org/W1607471841","https://openalex.org/W1985756506","https://openalex.org/W1988217924","https://openalex.org/W1988526405","https://openalex.org/W2011468011","https://openalex.org/W2026615874","https://openalex.org/W2028145673","https://openalex.org/W2038794597","https://openalex.org/W2041367235","https://openalex.org/W2076337359","https://openalex.org/W2092042957","https://openalex.org/W2095989982","https://openalex.org/W2096001037","https://openalex.org/W2097931172","https://openalex.org/W2107525266","https://openalex.org/W2110771465","https://openalex.org/W2116585932","https://openalex.org/W2118688707","https://openalex.org/W2118933070","https://openalex.org/W2119324175","https://openalex.org/W2127412976","https://openalex.org/W2132908009","https://openalex.org/W2145339207","https://openalex.org/W2147492008","https://openalex.org/W2151210636","https://openalex.org/W2152827112","https://openalex.org/W2161252410","https://openalex.org/W2168342951","https://openalex.org/W2168359464","https://openalex.org/W2185087676","https://openalex.org/W2197227940","https://openalex.org/W2225974540","https://openalex.org/W2257979135","https://openalex.org/W2334782222","https://openalex.org/W2751555667","https://openalex.org/W2950471160","https://openalex.org/W2951799221","https://openalex.org/W2962872206","https://openalex.org/W2962887844","https://openalex.org/W2963262099","https://openalex.org/W2963980401","https://openalex.org/W2964043796","https://openalex.org/W3011120880","https://openalex.org/W4214717370","https://openalex.org/W4233413206","https://openalex.org/W4247887198","https://openalex.org/W4249441547","https://openalex.org/W4253365321","https://openalex.org/W4297795161","https://openalex.org/W4298857966","https://openalex.org/W4394672593","https://openalex.org/W6600849757","https://openalex.org/W6657105691","https://openalex.org/W6677477928","https://openalex.org/W6677545834","https://openalex.org/W6679661297","https://openalex.org/W6682314434","https://openalex.org/W6685444567","https://openalex.org/W6689337587","https://openalex.org/W6692846177","https://openalex.org/W6696324988","https://openalex.org/W6703271639","https://openalex.org/W6731334075","https://openalex.org/W6775686901"],"related_works":["https://openalex.org/W2101355568","https://openalex.org/W3112319374","https://openalex.org/W4319083788","https://openalex.org/W3049166411","https://openalex.org/W4287688416","https://openalex.org/W2764311431","https://openalex.org/W4297789760","https://openalex.org/W56580342","https://openalex.org/W2492384539","https://openalex.org/W2765294391"],"abstract_inverted_index":{"Due":[0],"to":[1,85,94,102,120,183],"the":[2,8,23,39,56,59,72,91,98,108,110,121,133,137,142,147,155,159,162,165,171,174,177,184,200,204],"lack":[3],"of":[4,13,44,58,69,88,136,173,181],"enough":[5],"generalization":[6,54,167],"in":[7,22,33,42,55,71,80,97,107,141,146,154,176,203],"state":[9,35,74,92,96,143],"space,":[10],"common":[11],"methods":[12],"reinforcement":[14],"learning":[15,19,25,40,79,128,201],"suffer":[16],"from":[17,90,164,170],"slow":[18],"speed,":[20],"especially":[21],"early":[24,205],"trials.":[26,206],"This":[27],"paper":[28],"introduces":[29],"a":[30,67,81],"model-based":[31,127],"method":[32],"discrete":[34],"spaces":[36],"for":[37],"increasing":[38],"speed":[41,202],"terms":[43],"required":[45,49],"experiences":[46,57,89],"(but":[47],"not":[48,117],"computation":[50],"time)":[51],"by":[52,65,113],"exploiting":[53],"subspaces.":[60,148,178],"A":[61],"subspace":[62,82,115],"is":[63,187],"formed":[64],"choosing":[66],"subset":[68],"features":[70],"original":[73],"representation.":[75],"Generalization":[76],"and":[77,145],"faster":[78],"are":[83,152],"due":[84,101],"many-to-one":[86],"mapping":[87],"space":[93,144],"each":[95,114],"subspace.":[99],"Nevertheless,":[100],"inherent":[103],"perceptual":[104],"aliasing":[105],"(PA)":[106],"subspaces,":[109],"policy":[111,186],"suggested":[112],"does":[116],"generally":[118],"converge":[119],"optimal":[122,185],"policy.":[123],"Our":[124],"approach,":[125],"called":[126],"with":[129],"subspaces":[130],"(MoBLeSs),":[131],"calculates":[132],"confidence":[134,150],"intervals":[135,151],"estimated":[138],"Q":[139],"-values":[140],"These":[149],"used":[153],"decision-making,":[156],"such":[157],"that":[158,197],"agent":[160],"benefits":[161],"most":[163],"possible":[166],"while":[168],"avoiding":[169],"detriment":[172],"PA":[175],"The":[179],"convergence":[180],"MoBLeS":[182,198],"theoretically":[188],"investigated.":[189],"In":[190],"addition,":[191],"we":[192],"show":[193],"through":[194],"several":[195],"experiments":[196],"improves":[199]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}