{"id":"https://openalex.org/W602901760","doi":null,"title":"Sample-based Search Methods for Bayes-Adaptive Planning","display_name":"Sample-based Search Methods for Bayes-Adaptive Planning","publication_year":2015,"publication_date":"2015-02-28","ids":{"openalex":"https://openalex.org/W602901760","mag":"602901760"},"language":"en","primary_location":{"id":"pmh:oai:eprints.ucl.ac.uk.OAI2:1462170","doi":null,"is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/1462170/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Doctoral thesis, UCL (University College London).","raw_type":"Thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5009305837","display_name":"Arthur Guez","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"AG Guez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5009305837"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":23,"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":0.8809000253677368,"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":0.8809000253677368,"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":0.10890000313520432,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.0010999999940395355,"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/exploration-exploitation-trade-off","display_name":"exploration-exploitation balance","score":0.9419999718666077},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.7739999890327454},{"id":"https://openalex.org/keywords/simulation-based-planning","display_name":"simulation-based planning","score":0.6209999918937683},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.6840000152587891},{"id":"https://openalex.org/keywords/online-planning","display_name":"online planning","score":0.6370000243186951},{"id":"https://openalex.org/keywords/belief-updating","display_name":"belief updating","score":0.3569999933242798},{"id":"https://openalex.org/keywords/continuous-domains","display_name":"continuous domains","score":0.5960000157356262}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6759989857673645},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5896512866020203},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.5613911747932434},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5261352062225342},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.518342137336731},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.4473320245742798},{"id":"https://openalex.org/C207201462","wikidata":"https://www.wikidata.org/wiki/Q182505","display_name":"Bayes' theorem","level":3,"score":0.43910717964172363},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.43465813994407654},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.4299584925174713},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.35373011231422424},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3443076014518738},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3303823471069336},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.31387823820114136},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2397814691066742},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1904333233833313},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.11573156714439392},{"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":"pmh:oai:eprints.ucl.ac.uk.OAI2:1462170","doi":null,"is_oa":false,"landing_page_url":"https://discovery.ucl.ac.uk/id/eprint/1462170/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400024","display_name":"UCL Discovery (University College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I45129253","host_organization_name":"University College London","host_organization_lineage":["https://openalex.org/I45129253"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Doctoral thesis, UCL (University College London).","raw_type":"Thesis"},{"id":"mag:602901760","doi":null,"is_oa":false,"landing_page_url":"http://discovery.ucl.ac.uk/id/eprint/1462170/","pdf_url":null,"source":{"id":"https://openalex.org/S4306508231","display_name":"Doctoral thesis, UCL (University College London).","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Doctoral thesis, UCL (University College London).","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1975958074","https://openalex.org/W2077611535","https://openalex.org/W2119678437","https://openalex.org/W2914656440","https://openalex.org/W4298856952"],"related_works":["https://openalex.org/W2114275913","https://openalex.org/W2149586740","https://openalex.org/W2989165444","https://openalex.org/W2157477959","https://openalex.org/W7095190760","https://openalex.org/W2144794447","https://openalex.org/W3175974004","https://openalex.org/W7096993068","https://openalex.org/W7131400354","https://openalex.org/W2894616334"],"abstract_inverted_index":{"A":[0,26],"fundamental":[1],"issue":[2],"for":[3,86,143],"control":[4],"is":[5,49,79,94,172],"acting":[6],"in":[7,73,131,145,151,168,197,227,257,270,290],"the":[8,13,61,65,99,152,175,213,291],"face":[9],"of":[10,224,293],"uncertainty":[11],"about":[12,64],"environment.":[14,75],"Amongst":[15],"other":[16],"things,":[17],"this":[18],"induces":[19],"a":[20,35,53,81,90,169,220,283],"trade-off":[21],"between":[22,241],"exploration":[23,292],"and":[24,41,157,209,295],"exploitation.":[25],"model-based":[27],"Bayesian":[28,285],"agent":[29,286],"optimizes":[30],"its":[31,70],"return":[32],"by":[33,260,275],"maintaining":[34],"posterior":[36],"distribution":[37],"over":[38],"possible":[39,44],"environments,":[40],"considering":[42],"all":[43],"future":[45],"paths.":[46],"This":[47,76,245],"optimization":[48],"equivalent":[50],"to":[51,97,127,154,194,206,212,234,239,248],"solving":[52],"Markov":[54],"Decision":[55],"Process":[56],"(MDP)":[57],"whose":[58],"hyperstate":[59],"comprises":[60],"agent's":[62],"beliefs":[63],"environment,":[66],"as":[67,69,126],"well":[68,121],"current":[71,176],"state":[72],"that":[74,110,119,171,272,282],"corresponding":[77,100],"process":[78],"called":[80],"Bayes-Adaptive":[82],"MDP":[83],"(BAMDP).":[84],"Even":[85],"MDPs":[87,156,208],"with":[88,134,262],"only":[89,130],"few":[91],"states,":[92],"it":[93],"generally":[95],"intractable":[96],"solve":[98],"BAMDP":[101],"exactly.":[102],"Various":[103],"heuristics":[104],"have":[105],"been":[106],"devised,":[107],"but":[108],"those":[109,118],"are":[111,122,164,273],"computationally":[112],"tractable":[113,141],"often":[114],"perform":[115,120],"indifferently,":[116],"whereas":[117],"typically":[123],"so":[124],"expensive":[125,181],"be":[128,232,288],"applicable":[129],"small":[132],"domains":[133,259],"limited":[135],"structure.":[136],"Here,":[137],"we":[138,189,266],"develop":[139],"new":[140],"methods":[142,226,230],"planning":[144,269],"BAMDPs":[146],"based":[147],"on":[148,174],"recent":[149],"advances":[150],"solution":[153,215],"large":[155,207],"general":[158,222],"partially":[159],"observable":[160],"MDPs.":[161],"Our":[162],"algorithms":[163],"sample-based,":[165],"plan":[166],"online":[167],"way":[170],"focused":[173],"belief,":[177],"and,":[178],"critically,":[179],"avoid":[180],"belief":[182],"updates":[183],"during":[184,243],"simulations.":[185],"In":[186],"discrete":[187],"domains,":[188],"use":[190],"Monte-Carlo":[191],"tree":[192],"search":[193,195],"forward":[196],"an":[198],"aggressive":[199],"manner.":[200],"The":[201],"derived":[202],"algorithm":[203],"can":[204,231,287],"scale":[205],"provably":[210],"converges":[211],"Bayes-optimal":[214],"asymptotically.":[216],"We":[217,252,280],"then":[218],"consider":[219],"more":[221],"class":[223],"simulation-based":[225],"which":[228],"approximation":[229],"employed":[233],"allow":[235],"value":[236],"function":[237],"estimates":[238],"generalize":[240],"hyperstates":[242],"search.":[244],"allows":[246],"us":[247],"tackle":[249],"continuous":[250],"domains.":[251,299],"validate":[253],"our":[254],"approach":[255],"empirically":[256],"standard":[258],"comparison":[261],"existing":[263],"approximations.":[264],"Finally,":[265],"explore":[267],"Bayes-adaptive":[268],"environments":[271],"modelled":[274],"rich,":[276],"non-parametric":[277],"probabilistic":[278],"models.":[279],"demonstrate":[281],"fully":[284],"advantageous":[289],"complex":[294],"even":[296],"infinite,":[297],"structured":[298]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}