{"id":"https://openalex.org/W7099280790","doi":null,"title":"Bayes-Adaptive POMDPs: Toward an Optimal Policy for Learning POMDPs with Parameter Uncertainty","display_name":"Bayes-Adaptive POMDPs: Toward an Optimal Policy for Learning POMDPs with Parameter Uncertainty","alternate_titles":[],"publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W7099280790"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.132.7043","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.132.7043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.mcgill.ca/~sross12/publications/Ross-McGill-COMP652-ProjectReport.pdf","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W7099280790"],"child_works_count":0,"type":"article","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/A5057087592","display_name":"St\u00e9phane Ross","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"contributor_roles":[],"raw_author_name":"St\u00e9phane Ross","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5057087592"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"reviewed_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_pulled":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9970999956130981,"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":0.9970999956130981,"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":0.0013000000035390258,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.9639999866485596},{"id":"https://openalex.org/keywords/parameter-uncertainty","display_name":"parameter uncertainty","score":0.9639999866485596},{"id":"https://openalex.org/keywords/exploration-exploitation-trade-off","display_name":"exploration-exploitation balance","score":0.9649999737739563},{"id":"https://openalex.org/keywords/optimal-policy","display_name":"optimal policy","score":0.7360000014305115},{"id":"https://openalex.org/keywords/infinite-state-spaces","display_name":"infinite state spaces","score":0.5740000009536743},{"id":"https://openalex.org/keywords/approximate-algorithms","display_name":"approximate algorithms","score":0.6700000166893005},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.9010000228881836}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.957099974155426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6115000247955322},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5371000170707703},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4345000088214874},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.40540000796318054},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.39329999685287476},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.362199991941452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31470000743865967},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.31310001015663147},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2833000123500824},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.132.7043","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.132.7043","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.mcgill.ca/~sross12/publications/Ross-McGill-COMP652-ProjectReport.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2144794447","https://openalex.org/W2404879558","https://openalex.org/W7096677896","https://openalex.org/W7098031390","https://openalex.org/W7096590101","https://openalex.org/W7095190760","https://openalex.org/W7097500431","https://openalex.org/W2135681007","https://openalex.org/W2741438342"],"abstract_inverted_index":{"Abstract.":[0],"Most":[1],"of":[2,48,82,94,108,159,175],"the":[3,19,23,36,46,49,55,63,67,70,92,100,106,109,116,147,152,169],"POMDP":[4,24,50,64,110,126,154],"litterature":[5],"as":[6,111],"focused":[7],"on":[8],"developping":[9],"new":[10,87,124],"approximate":[11,164],"algorithms":[12],"to":[13,54,65,85],"solve":[14,168],"ever":[15],"larger":[16],"POMDPs,":[17],"under":[18],"general":[20],"assumption":[21],"that":[22,45,129,138,166],"model":[25,107,127],"is":[26,34,81,113],"known":[27,77],"a":[28,123,172],"priori.":[29],"In":[30],"practice,":[31],"however":[32],"this":[33,119],"rarely":[35,76],"case.":[37],"For":[38],"instance,":[39],"robot":[40],"navigation":[41],"problems":[42],"generally":[43],"require":[44],"parameters":[47,74,96],"be":[51],"well":[52],"tuned":[53],"robot\u2019s":[56],"sensors":[57],"and":[58,72,103],"actuators":[59],"in":[60,115,171],"order":[61],"for":[62],"reflect":[66],"reality,":[68],"but":[69],"sensor":[71],"actuator":[73],"are":[75],"precisely.":[78],"Hence":[79],"it":[80],"crucial":[83],"importance":[84],"develop":[86],"approaches":[88],"which":[89],"can":[90,167],"take":[91],"uncertainty":[93],"these":[95],"into":[97,145],"account":[98,146],"during":[99],"planning":[101],"process":[102],"further":[104],"refine":[105],"experience":[112],"acquired":[114],"environment.":[117],"To":[118],"end,":[120],"we":[121,161],"formulate":[122],"Bayes-Adaptive":[125,153],"such":[128],"its":[130],"optimal":[131,135],"policy":[132],"provide":[133],"an":[134,156,163],"exploration-exploitation":[136],"tradeoff":[137],"will":[139],"maximize":[140],"long-term":[141],"reward":[142],"while":[143],"taking":[144],"parameter":[148],"uncertainty.":[149],"However,":[150],"since":[151],"has":[155],"infinite":[157],"number":[158],"states,":[160],"propose":[162],"algorithm":[165],"problem":[170],"reasonable":[173],"ammount":[174],"time.":[176],"1":[177]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7099280790","counts_by_year":[{"year":2013,"cited_by_count":2}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2025-10-27T00:00:00"}
