{"id":"https://openalex.org/W3004707083","doi":"https://doi.org/10.5555/1953048.2021055","title":"A Bayesian Approach for Learning and Planning in Partially Observable Markov Decision Processes","display_name":"A Bayesian Approach for Learning and Planning in Partially Observable Markov Decision Processes","publication_year":2011,"publication_date":"2011-07-01","ids":{"openalex":"https://openalex.org/W3004707083","doi":"https://doi.org/10.5555/1953048.2021055","mag":"3004707083"},"language":"en","primary_location":{"id":"mag:3004707083","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/1953048.2021055","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Journal of Machine Learning Research","raw_type":null},"type":"article","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/A5078130945","display_name":"RossSt\u00e9phane","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"RossSt\u00e9phane","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006496586","display_name":"PineauJoelle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"PineauJoelle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034010693","display_name":"Chaib-draaBrahim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chaib-draaBrahim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028013927","display_name":"KreitmannPierre","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"KreitmannPierre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5883,"has_fulltext":false,"cited_by_count":62,"citation_normalized_percentile":{"value":0.91277433,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"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":0.6639000177383423,"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":0.6639000177383423,"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/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.6501588821411133},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6255545020103455},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6096317172050476},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5991812348365784},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.5696141719818115},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5429200530052185},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5019495487213135},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.41246891021728516},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.32658326625823975},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.27224934101104736},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22925251722335815},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09448114037513733}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.6501588821411133},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6255545020103455},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6096317172050476},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5991812348365784},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.5696141719818115},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5429200530052185},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5019495487213135},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41246891021728516},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.32658326625823975},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.27224934101104736},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22925251722335815},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09448114037513733},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:3004707083","is_oa":false,"landing_page_url":"https://dl.acm.org/doi/10.5555/1953048.2021055","pdf_url":null,"source":{"id":"https://openalex.org/S118988714","display_name":"Journal of Machine Learning Research","issn_l":"1532-4435","issn":["1532-4435","1533-7928"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310315718","host_organization_name":"The MIT Press","host_organization_lineage":["https://openalex.org/P4310315718"],"host_organization_lineage_names":["The MIT Press"],"type":"journal"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Journal of Machine Learning Research","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2168839459","https://openalex.org/W2152707121","https://openalex.org/W2909739305","https://openalex.org/W2168318917","https://openalex.org/W2144794447","https://openalex.org/W2404879558","https://openalex.org/W2128643385","https://openalex.org/W2019342219","https://openalex.org/W2169743339","https://openalex.org/W2044097402","https://openalex.org/W2083849869","https://openalex.org/W2128098349","https://openalex.org/W1970837196","https://openalex.org/W2043552103","https://openalex.org/W1548514401","https://openalex.org/W1988667012","https://openalex.org/W47969833","https://openalex.org/W2950276012","https://openalex.org/W2381909226","https://openalex.org/W1486120571"],"abstract_inverted_index":{"Bayesian":[0,23],"learning":[1],"methods":[2],"have":[3],"recently":[4],"been":[5],"shown":[6],"to":[7,12],"provide":[8],"an":[9],"elegant":[10],"solution":[11],"the":[13],"exploration-exploitation":[14],"trade-off":[15],"in":[16],"reinforcement":[17],"learning.":[18],"However":[19],"most":[20],"investigations":[21],"of":[22],"reinfo...":[24]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-10-10T17:16:08.811792","created_date":"2025-10-10T00:00:00"}