{"id":"https://openalex.org/W50830905","doi":null,"title":"Learning and acting in unknown and uncertain worlds","display_name":"Learning and acting in unknown and uncertain worlds","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W50830905","mag":"50830905"},"language":"en","primary_location":{"id":"pmh:oai:etheses.bham.ac.uk:1656","doi":null,"is_oa":false,"landing_page_url":"http://etheses.bham.ac.uk/1656/1/Welsh11PhD.pdf","pdf_url":"http://etheses.bham.ac.uk/1656/1/Welsh11PhD.pdf","source":{"id":"https://openalex.org/S4306402357","display_name":"University of Birmingham Institutional Research Archive (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10068/981922","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055382092","display_name":"Noel Welsh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Noel Welsh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5055382092"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":9.999999747378752e-05,"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":9.999999747378752e-05,"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/model-free-reinforcement-learning","display_name":"model-free reinforcement learning","score":0.8119999766349792},{"id":"https://openalex.org/keywords/model-learning","display_name":"model learning","score":0.8920000195503235},{"id":"https://openalex.org/keywords/policy-search","display_name":"policy search","score":0.7279999852180481},{"id":"https://openalex.org/keywords/information-sharing","display_name":"information sharing","score":0.8050000071525574},{"id":"https://openalex.org/keywords/variational-bayesian-inference","display_name":"variational inference","score":0.6480000019073486},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.527999997138977},{"id":"https://openalex.org/keywords/noisy-environments","display_name":"noisy environments","score":0.6470000147819519},{"id":"https://openalex.org/keywords/memory-capacity","display_name":"memory capacity","score":0.40299999713897705}],"concepts":[{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6145232319831848},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.605679452419281},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5854772925376892},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.5834282040596008},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.5325049161911011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5274115800857544},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.43085065484046936},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.4271122217178345},{"id":"https://openalex.org/C2776854237","wikidata":"https://www.wikidata.org/wiki/Q6031064","display_name":"Information sharing","level":2,"score":0.41138774156570435},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4046471118927002},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.16458278894424438},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.10463222861289978},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:etheses.bham.ac.uk:1656","doi":null,"is_oa":false,"landing_page_url":"http://etheses.bham.ac.uk/1656/1/Welsh11PhD.pdf","pdf_url":"http://etheses.bham.ac.uk/1656/1/Welsh11PhD.pdf","source":{"id":"https://openalex.org/S4306402357","display_name":"University of Birmingham Institutional Research Archive (University of Birmingham)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79619799","host_organization_name":"University of Birmingham","host_organization_lineage":["https://openalex.org/I79619799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"pmh:oai:uilis.unsyiah.ac.id:45591","doi":null,"is_oa":false,"landing_page_url":"http://uilis.unsyiah.ac.id/opentheses/items/show/45591","pdf_url":null,"source":{"id":"https://openalex.org/S4377196378","display_name":"UPT. Syiah Kuala University Library (Syiah Kuala University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I187494767","host_organization_name":"Universitas Syiah Kuala","host_organization_lineage":["https://openalex.org/I187494767"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Thesis"},{"id":"pmh:hdl:10068/981922","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10068/981922","pdf_url":null,"source":{"id":"https://openalex.org/S4377196900","display_name":"OpenGrey (Institut de l'Information Scientifique et Technique)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1295345811","host_organization_name":"Institut de l'Information Scientifique et Technique","host_organization_lineage":["https://openalex.org/I1295345811"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"U - Thesis"},{"id":"mag:50830905","doi":null,"is_oa":false,"landing_page_url":"https://etheses.bham.ac.uk/id/eprint/1656/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:hdl:10068/981922","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/10068/981922","pdf_url":null,"source":{"id":"https://openalex.org/S4377196900","display_name":"OpenGrey (Institut de l'Information Scientifique et Technique)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1295345811","host_organization_name":"Institut de l'Information Scientifique et Technique","host_organization_lineage":["https://openalex.org/I1295345811"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"U - Thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":121,"referenced_works":["https://openalex.org/W6242441","https://openalex.org/W27992807","https://openalex.org/W32785352","https://openalex.org/W158205031","https://openalex.org/W180325379","https://openalex.org/W181022050","https://openalex.org/W195465510","https://openalex.org/W1176136657","https://openalex.org/W1486341833","https://openalex.org/W1489119587","https://openalex.org/W1489258026","https://openalex.org/W1496855202","https://openalex.org/W1515891729","https://openalex.org/W1517266559","https://openalex.org/W1526654727","https://openalex.org/W1529851927","https://openalex.org/W1535392723","https://openalex.org/W1539054658","https://openalex.org/W1540337045","https://openalex.org/W1541084404","https://openalex.org/W1557073320","https://openalex.org/W1568770747","https://openalex.org/W1570690983","https://openalex.org/W1572411218","https://openalex.org/W1583380718","https://openalex.org/W1594297126","https://openalex.org/W1594783240","https://openalex.org/W1599296339","https://openalex.org/W1617610651","https://openalex.org/W1640774615","https://openalex.org/W1657542410","https://openalex.org/W1657674574","https://openalex.org/W1677409904","https://openalex.org/W1683541793","https://openalex.org/W1687873425","https://openalex.org/W1712653483","https://openalex.org/W1766015196","https://openalex.org/W1825640910","https://openalex.org/W1850488217","https://openalex.org/W1914583973","https://openalex.org/W1961810468","https://openalex.org/W1967687583","https://openalex.org/W1970789124","https://openalex.org/W1984205520","https://openalex.org/W1987532879","https://openalex.org/W1994920552","https://openalex.org/W2011058337","https://openalex.org/W2011671528","https://openalex.org/W2013391942","https://openalex.org/W2018122853","https://openalex.org/W2020999234","https://openalex.org/W2024060531","https://openalex.org/W2031594824","https://openalex.org/W2034725503","https://openalex.org/W2049633694","https://openalex.org/W2050234982","https://openalex.org/W2052014837","https://openalex.org/W2052627427","https://openalex.org/W2064675550","https://openalex.org/W2069429561","https://openalex.org/W2079987671","https://openalex.org/W2081547991","https://openalex.org/W2083875149","https://openalex.org/W2089484716","https://openalex.org/W2096533821","https://openalex.org/W2097936260","https://openalex.org/W2099291701","https://openalex.org/W2102379184","https://openalex.org/W2103581399","https://openalex.org/W2104209160","https://openalex.org/W2104368525","https://openalex.org/W2106008679","https://openalex.org/W2107726111","https://openalex.org/W2108519123","https://openalex.org/W2113958614","https://openalex.org/W2115979064","https://openalex.org/W2119567691","https://openalex.org/W2122410182","https://openalex.org/W2123372395","https://openalex.org/W2125523964","https://openalex.org/W2125792273","https://openalex.org/W2125838338","https://openalex.org/W2128002512","https://openalex.org/W2128775537","https://openalex.org/W2130801532","https://openalex.org/W2134802714","https://openalex.org/W2135194391","https://openalex.org/W2139302369","https://openalex.org/W2140881794","https://openalex.org/W2141690016","https://openalex.org/W2144794447","https://openalex.org/W2144824356","https://openalex.org/W2144913588","https://openalex.org/W2147000823","https://openalex.org/W2147249804","https://openalex.org/W2148067905","https://openalex.org/W2151040408","https://openalex.org/W2151103935","https://openalex.org/W2151967501","https://openalex.org/W2153727510","https://openalex.org/W2154642048","https://openalex.org/W2157769062","https://openalex.org/W2158190429","https://openalex.org/W2158266063","https://openalex.org/W2158640361","https://openalex.org/W2159498728","https://openalex.org/W2160067530","https://openalex.org/W2162995740","https://openalex.org/W2164892942","https://openalex.org/W2167810193","https://openalex.org/W2168359464","https://openalex.org/W2169895393","https://openalex.org/W2172182983","https://openalex.org/W2172246523","https://openalex.org/W2183998037","https://openalex.org/W2293047233","https://openalex.org/W2567948266","https://openalex.org/W2611243847","https://openalex.org/W2952902960","https://openalex.org/W2963124974","https://openalex.org/W6884728263"],"related_works":["https://openalex.org/W1497039698","https://openalex.org/W1526144783","https://openalex.org/W2564518165","https://openalex.org/W4403793005","https://openalex.org/W111328409","https://openalex.org/W2211585684","https://openalex.org/W1580557482","https://openalex.org/W7018681770","https://openalex.org/W2135681007","https://openalex.org/W3182023855"],"abstract_inverted_index":{"This":[0,15],"dissertation":[1,164],"addresses":[2],"the":[3,70,82,87,97,100,105,119,130,146,191,243,276,333],"problem":[4],"of":[5,69,81,99,107,114,138,148,162,173,204,210,212,232,246,332],"learning":[6,184,187,266,313],"to":[7,35,38,55,62,64,77,118,142,178,255,275,306],"act":[8,65,143],"in":[9,126],"an":[10,27,40,134],"unknown":[11],"and":[12,72,185,235,281,298,336],"uncertain":[13],"world.":[14,88],"is":[16,25,33,52,109,116,122,140,155,165,238,260],"a":[17,22,67,79,93,111,127,157,195,201,208,230,261,315,318,323],"difficult":[18],"problem.":[19,181],"Even":[20],"if":[21],"world":[23,50],"model":[24,51,68,73,80,101,186,256,312,334],"available,":[26],"assumption":[28],"not":[29],"made":[30],"here,":[31],"it":[32,223,271],"known":[34,53,124],"be":[36,342],"intractable":[37],"learn":[39,63,78,225],"optimal":[41,227],"policy":[42,103,196],"for":[43,229,265,314],"controlling":[44],"behaviour":[45],"(Littman":[46],"1996).":[47],"Assuming":[48],"no":[49,330],"leads":[54,305],"two":[56,253],"approaches:":[57],"model-free":[58,183],"learning,":[59,74],"which":[60,75,108],"attempts":[61,76],"without":[66,248],"environment,":[71,129],"environment":[83,135,171],"from":[84,344],"interactions":[85,152],"with":[86,200,347],"Most":[89],"earlier":[90],"approaches":[91,254],"make":[92],"priori":[94],"assumptions":[95,294,304],"about":[96,295],"complexity":[98],"or":[102,170],"required,":[104],"upshot":[106],"that":[110,125,166,206,222,236,270,301,328,339],"fixed":[112],"amount":[113,137,245],"memory":[115,139,149],"available":[117],"agent.":[120],"It":[121],"well":[123],"noisy":[128],"type":[131],"assumed":[132],"within,":[133],"specific":[136],"required":[141],"optimally.":[144],"Fixing":[145],"capacity":[147],"before":[150],"any":[151],"have":[153],"occurred":[154],"thus":[156],"limiting":[158],"assumption.":[159],"The":[160,258],"theme":[161],"this":[163,180,289],"representing":[167],"multiple":[168],"policies":[169,211,219,228],"models":[172],"varying":[174,213],"size":[175],"enables":[176],"us":[177],"address":[179,311],"Both":[182],"are":[188],"investigated.":[189],"For":[190],"former,":[192],"I":[193,220,251,268,299,309,321],"present":[194],"search":[197],"method":[198,264],"(usable":[199],"wide":[202],"range":[203],"algorithms)":[205],"maintains":[207],"population":[209],"size.":[214],"By":[215],"sharing":[216],"information":[217,249],"between":[218],"show":[221,269,300,337],"can":[224,341],"near":[226],"variety":[231],"challenging":[233],"problems,":[234],"performance":[237],"significantly":[239],"improved":[240],"over":[241],"using":[242,284],"same":[244],"computation":[247],"sharing.":[250],"investigate":[252],"learning.":[257],"first":[259],"variational":[262],"Bayesian":[263,326],"POMDPs.":[267],"achieves":[272],"superior":[273],"results":[274],"Bayes-adaptive":[277],"algorithm":[278],"(Ross,":[279],"Chaib-draa":[280],"Pineau":[282],"2007)":[283],"their":[285],"experimental":[286,290],"setup.":[287],"However,":[288],"setup":[291],"makes":[292],"strong":[293],"prior":[296,349],"information,":[297],"weakening":[302],"these":[303],"poor":[307],"performance.":[308],"then":[310],"simpler":[316],"model,":[317],"topological":[319],"map.":[320],"develop":[322],"novel":[324],"non-parametric":[325],"map":[327],"sets":[329],"limit":[331],"size,":[335],"experimentally":[338],"maps":[340],"learned":[343],"robot":[345],"data":[346],"weak":[348],"knowledge.":[350]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}