{"id":"https://openalex.org/W2124434282","doi":"https://doi.org/10.1109/3477.499796","title":"Hidden state and reinforcement learning with instance-based state identification","display_name":"Hidden state and reinforcement learning with instance-based state identification","publication_year":1996,"publication_date":"1996-06-01","ids":{"openalex":"https://openalex.org/W2124434282","doi":"https://doi.org/10.1109/3477.499796","mag":"2124434282","pmid":"https://pubmed.ncbi.nlm.nih.gov/18263047"},"language":"en","primary_location":{"id":"doi:10.1109/3477.499796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3477.499796","pdf_url":null,"source":{"id":"https://openalex.org/S4210170378","display_name":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","issn_l":"1083-4419","issn":["1083-4419","1941-0492"],"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 Systems, Man and Cybernetics, Part B (Cybernetics)","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/A5004956398","display_name":"R. Andrew McCallum","orcid":null},"institutions":[{"id":"https://openalex.org/I5388228","display_name":"University of Rochester","ror":"https://ror.org/022kthw22","country_code":"US","type":"education","lineage":["https://openalex.org/I5388228"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"R.A. McCallum","raw_affiliation_strings":["Dept. of Comput. Sci., Rochester Univ., NY","Dept. of Comput. Sci. Rochester Univ., NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Comput. Sci., Rochester Univ., NY","institution_ids":["https://openalex.org/I5388228"]},{"raw_affiliation_string":"Dept. of Comput. Sci. Rochester Univ., NY, USA","institution_ids":["https://openalex.org/I5388228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5004956398"],"corresponding_institution_ids":["https://openalex.org/I5388228"],"apc_list":null,"apc_paid":null,"fwci":6.2771,"has_fulltext":false,"cited_by_count":75,"citation_normalized_percentile":{"value":0.96829816,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"26","issue":"3","first_page":"464","last_page":"473"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.9979000091552734,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9833999872207642,"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/computer-science","display_name":"Computer science","score":0.6758836507797241},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6752936244010925},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.658085823059082},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5508888363838196},{"id":"https://openalex.org/keywords/state-space","display_name":"State space","score":0.5312744379043579},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5030452609062195},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.49666768312454224},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.47925567626953125},{"id":"https://openalex.org/keywords/conditional-random-field","display_name":"Conditional random field","score":0.4385797381401062},{"id":"https://openalex.org/keywords/boltzmann-machine","display_name":"Boltzmann machine","score":0.4161229133605957},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4157985746860504},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4108266830444336},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4104105532169342},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3720274269580841},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.12624064087867737},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10564360022544861}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6758836507797241},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6752936244010925},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.658085823059082},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5508888363838196},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5312744379043579},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5030452609062195},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.49666768312454224},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.47925567626953125},{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.4385797381401062},{"id":"https://openalex.org/C192576344","wikidata":"https://www.wikidata.org/wiki/Q194706","display_name":"Boltzmann machine","level":3,"score":0.4161229133605957},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4157985746860504},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4108266830444336},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4104105532169342},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3720274269580841},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.12624064087867737},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10564360022544861},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/3477.499796","is_oa":false,"landing_page_url":"https://doi.org/10.1109/3477.499796","pdf_url":null,"source":{"id":"https://openalex.org/S4210170378","display_name":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","issn_l":"1083-4419","issn":["1083-4419","1941-0492"],"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 Systems, Man and Cybernetics, Part B (Cybernetics)","raw_type":"journal-article"},{"id":"pmid:18263047","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18263047","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 systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society","raw_type":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.38.6696","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.38.6696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cs.rochester.edu/pub/papers/robotics/96.mccallum-ieee.ps.Z","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W95627046","https://openalex.org/W1488696015","https://openalex.org/W1488778327","https://openalex.org/W1497256448","https://openalex.org/W1499371387","https://openalex.org/W1505156375","https://openalex.org/W1555801537","https://openalex.org/W1576818901","https://openalex.org/W1595483645","https://openalex.org/W1610678877","https://openalex.org/W1657674574","https://openalex.org/W1687873425","https://openalex.org/W1965367179","https://openalex.org/W1987780311","https://openalex.org/W2002444764","https://openalex.org/W2013616412","https://openalex.org/W2049633694","https://openalex.org/W2054804336","https://openalex.org/W2065356613","https://openalex.org/W2091565802","https://openalex.org/W2099873296","https://openalex.org/W2100948575","https://openalex.org/W2103537992","https://openalex.org/W2125011004","https://openalex.org/W2134814908","https://openalex.org/W2140095144","https://openalex.org/W2160067530","https://openalex.org/W2288623399","https://openalex.org/W2345941287","https://openalex.org/W2346653309","https://openalex.org/W2465828773","https://openalex.org/W3017143921","https://openalex.org/W3037058914","https://openalex.org/W4233148159","https://openalex.org/W4254384028","https://openalex.org/W4301958881","https://openalex.org/W6629993198","https://openalex.org/W6636922475","https://openalex.org/W6674711614","https://openalex.org/W6683935339","https://openalex.org/W6704554953"],"related_works":["https://openalex.org/W2356597680","https://openalex.org/W2916681395","https://openalex.org/W2114846443","https://openalex.org/W3102147106","https://openalex.org/W4225571923","https://openalex.org/W3212257828","https://openalex.org/W2999580272","https://openalex.org/W4297873223","https://openalex.org/W2350784623","https://openalex.org/W2126211886"],"abstract_inverted_index":{"Real":[0],"robots":[1],"with":[2,75,102,107,115,173],"real":[3],"sensors":[4,23],"are":[5],"not":[6],"omniscient.":[7],"When":[8],"a":[9,96,151],"robot's":[10],"next":[11],"course":[12],"of":[13,25,34,81,133,147,165,176],"action":[14],"depends":[15],"on":[16],"information":[17,54],"that":[18,105,113,126],"is":[19,85],"hidden":[20,46,57],"from":[21,44],"the":[22,41,45,124,131,134,137],"because":[24],"problems":[26],"such":[27],"as":[28],"occlusion,":[29],"restricted":[30],"range,":[31],"bounded":[32],"field":[33],"view":[35],"and":[36,72,117],"limited":[37],"attention,":[38],"we":[39,155],"say":[40],"robot":[42],"suffers":[43],"state":[47,67,94,103,135],"problem.":[48],"State":[49],"identification":[50,104],"techniques":[51,84],"use":[52],"history":[53,64,116,145],"to":[55,62,99,144],"uncover":[56],"state.":[58],"Some":[59],"previous":[60,182],"approaches":[61],"encoding":[63],"include:":[65],"finite":[66],"machines,":[68],"recurrent":[69],"neural":[70],"networks":[71],"genetic":[73],"programming":[74],"indexed":[76],"memory.":[77],"A":[78],"chief":[79],"disadvantage":[80],"all":[82],"these":[83],"their":[86],"long":[87],"training":[88,110],"time.":[89],"This":[90],"paper":[91],"presents":[92],"instance-based":[93,140],"identification,":[95],"new":[97],"approach":[98,138],"reinforcement":[100],"learning":[101,114,118,143],"learns":[106,172],"much":[108],"fewer":[109,178],"steps.":[111],"Noting":[112],"in":[119,150,158],"continuous":[120,152],"spaces":[121],"both":[122],"share":[123],"property":[125],"they":[127],"begin":[128],"without":[129],"knowing":[130],"granularity":[132],"space,":[136,154],"applies":[139],"(or":[141],"\"memory-based\")":[142],"sequences-instead":[146],"recording":[148],"instances":[149,157],"geometrical":[153],"record":[156],"action-percept-reward":[159],"sequence":[160],"space.":[161],"The":[162],"first":[163],"implementation":[164],"this":[166],"approach,":[167],"called":[168],"Nearest":[169],"Sequence":[170],"Memory,":[171],"an":[174],"order":[175],"magnitude":[177],"steps":[179],"than":[180],"several":[181],"approaches.":[183]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}