{"id":"https://openalex.org/W2001339644","doi":"https://doi.org/10.1145/2414416.2414420","title":"Bayesian Learning of Noisy Markov Decision Processes","display_name":"Bayesian Learning of Noisy Markov Decision Processes","publication_year":2013,"publication_date":"2013-01-01","ids":{"openalex":"https://openalex.org/W2001339644","doi":"https://doi.org/10.1145/2414416.2414420","mag":"2001339644"},"language":"en","primary_location":{"id":"doi:10.1145/2414416.2414420","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2414416.2414420","pdf_url":null,"source":{"id":"https://openalex.org/S38703467","display_name":"ACM Transactions on Modeling and Computer Simulation","issn_l":"1049-3301","issn":["1049-3301","1558-1195"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Modeling and Computer Simulation","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5035598384","display_name":"Sumeetpal S. Singh","orcid":"https://orcid.org/0000-0002-5430-1496"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Sumeetpal S. Singh","raw_affiliation_strings":["University of Cambridge","University of Cambridge,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Cambridge","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"University of Cambridge,","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059273710","display_name":"ChopinNicolas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137396","display_name":"Centre de Recherche en \u00c9conomie et Statistique","ror":"https://ror.org/0449khs19","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I142476485","https://openalex.org/I4210108488","https://openalex.org/I4210108488","https://openalex.org/I4210137396","https://openalex.org/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4210150854","https://openalex.org/I84009706"]},{"id":"https://openalex.org/I83860666","display_name":"HEC Paris","ror":"https://ror.org/0423jsj19","country_code":"FR","type":"education","lineage":["https://openalex.org/I83860666"]},{"id":"https://openalex.org/I84009706","display_name":"ENSAE Paris","ror":"https://ror.org/01fz7mn40","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108488","https://openalex.org/I4210145102","https://openalex.org/I84009706"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Chopin","raw_affiliation_strings":["CREST---ENSAE and HEC Paris","CREST (ENSAE) and HEC Paris#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CREST---ENSAE and HEC Paris","institution_ids":["https://openalex.org/I84009706","https://openalex.org/I4210137396","https://openalex.org/I83860666"]},{"raw_affiliation_string":"CREST (ENSAE) and HEC Paris#TAB#","institution_ids":["https://openalex.org/I83860666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018876311","display_name":"Nick Whiteley","orcid":"https://orcid.org/0000-0002-8337-626X"},"institutions":[{"id":"https://openalex.org/I36234482","display_name":"University of Bristol","ror":"https://ror.org/0524sp257","country_code":"GB","type":"education","lineage":["https://openalex.org/I36234482"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Nick Whiteley","raw_affiliation_strings":["University of Bristol"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Bristol","institution_ids":["https://openalex.org/I36234482"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9883,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.81906892,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"23","issue":"1","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9934999942779541,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.9934999942779541,"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/T11236","display_name":"Control Systems and Identification","score":0.9864000082015991,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10136","display_name":"Statistical Methods and Inference","score":0.9832000136375427,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-chain-monte-carlo","display_name":"Markov chain Monte Carlo","score":0.7457154989242554},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6432750225067139},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5864668488502502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5539231300354004},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.5485674738883972},{"id":"https://openalex.org/keywords/variable-order-bayesian-network","display_name":"Variable-order Bayesian network","score":0.5034942030906677},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.49814295768737793},{"id":"https://openalex.org/keywords/bayesian-inference","display_name":"Bayesian inference","score":0.4708373546600342},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4452967941761017},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4391118884086609},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.4291578531265259},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.41630181670188904},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3312762975692749},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.2988136112689972},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24821549654006958},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.11334043741226196}],"concepts":[{"id":"https://openalex.org/C111350023","wikidata":"https://www.wikidata.org/wiki/Q1191869","display_name":"Markov chain Monte Carlo","level":3,"score":0.7457154989242554},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6432750225067139},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5864668488502502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5539231300354004},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.5485674738883972},{"id":"https://openalex.org/C71983512","wikidata":"https://www.wikidata.org/wiki/Q7915687","display_name":"Variable-order Bayesian network","level":4,"score":0.5034942030906677},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.49814295768737793},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.4708373546600342},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4452967941761017},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4391118884086609},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.4291578531265259},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.41630181670188904},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3312762975692749},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.2988136112689972},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24821549654006958},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.11334043741226196}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2414416.2414420","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2414416.2414420","pdf_url":null,"source":{"id":"https://openalex.org/S38703467","display_name":"ACM Transactions on Modeling and Computer Simulation","issn_l":"1049-3301","issn":["1049-3301","1558-1195"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Modeling and Computer Simulation","raw_type":"journal-article"},{"id":"pmh:oai:research-information.bris.ac.uk:openaire_cris_publications/9171b686-c986-4ff8-9d0f-874e14fd6d5e","is_oa":false,"landing_page_url":"https://research-information.bris.ac.uk/en/publications/9171b686-c986-4ff8-9d0f-874e14fd6d5e","pdf_url":null,"source":{"id":"https://openalex.org/S7407055359","display_name":"Explore Bristol Research","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Singh, S, Chopin, N & Whiteley, N 2013, 'Bayesian Learning of Noisy Markov Decision Processes', ACM Transactions on Modeling and Computer Simulation. https://doi.org/10.1145/2414416.2414420","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:HAL:hal-02403299v1","is_oa":false,"landing_page_url":"https://hal.science/hal-02403299","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ACM Transactions on Modeling and Computer Simulation, 2013, 23 (1), pp.1-25. ⟨10.1145/2414416.2414420⟩","raw_type":"Journal articles"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.8100000023841858,"display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G2357053151","display_name":null,"funder_award_id":"ANS-008-BLAN-0218 BigMC","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W621546036","https://openalex.org/W1508268337","https://openalex.org/W1524366261","https://openalex.org/W1538737402","https://openalex.org/W1576452626","https://openalex.org/W1983980258","https://openalex.org/W1984454144","https://openalex.org/W1996993126","https://openalex.org/W1999874108","https://openalex.org/W2013614847","https://openalex.org/W2040766536","https://openalex.org/W2051378923","https://openalex.org/W2059183841","https://openalex.org/W2061562262","https://openalex.org/W2063009186","https://openalex.org/W2064387721","https://openalex.org/W2067226652","https://openalex.org/W2075453090","https://openalex.org/W2090854863","https://openalex.org/W2098432798","https://openalex.org/W2098601118","https://openalex.org/W2104335146","https://openalex.org/W2108306139","https://openalex.org/W2117569500","https://openalex.org/W2127572219","https://openalex.org/W2137307912","https://openalex.org/W2147357149","https://openalex.org/W2152977846","https://openalex.org/W2167128659","https://openalex.org/W2170481316","https://openalex.org/W2478818565","https://openalex.org/W3021862730","https://openalex.org/W3023432200","https://openalex.org/W3102222826","https://openalex.org/W4233612155","https://openalex.org/W4254147434"],"related_works":["https://openalex.org/W2096013579","https://openalex.org/W1589140671","https://openalex.org/W1760611253","https://openalex.org/W52153049","https://openalex.org/W2951545791","https://openalex.org/W1515117609","https://openalex.org/W2294884454","https://openalex.org/W4323315247","https://openalex.org/W2464065341","https://openalex.org/W4283077537"],"abstract_inverted_index":{"We":[0,25],"consider":[1],"the":[2,9,35,54,84,105,111],"inverse":[3],"reinforcement":[4],"learning":[5,12,116],"problem,":[6],"that":[7],"is,":[8],"problem":[10],"of":[11,37,53,104],"from,":[13],"and":[14,59],"then":[15],"predicting":[16],"or":[17],"mimicking":[18],"a":[19,27,38,43,68,90,117],"controller":[20],"based":[21],"on":[22],"state/action":[23],"data.":[24],"propose":[26],"statistical":[28],"model":[29,55],"for":[30,81,100],"such":[31],"data,":[32],"derived":[33],"from":[34,83],"structure":[36],"Markov":[39,73],"decision":[40],"process.":[41],"Adopting":[42],"Bayesian":[44],"approach":[45],"to":[46,97,115],"inference,":[47],"we":[48],"show":[49],"how":[50,60],"latent":[51],"variables":[52],"can":[56,64],"be":[57,65,98],"estimated,":[58],"predictions":[61],"about":[62],"actions":[63],"made,":[66],"in":[67],"unified":[69],"framework.":[70],"A":[71],"new":[72],"chain":[74],"Monte":[75],"Carlo":[76],"(MCMC)":[77],"sampler":[78],"is":[79,95,113],"devised":[80],"simulation":[82],"posterior":[85],"distribution.":[86],"This":[87],"step":[88],"includes":[89],"parameter":[91],"expansion":[92],"step,":[93],"which":[94],"shown":[96],"essential":[99],"good":[101],"convergence":[102],"properties":[103],"MCMC":[106],"sampler.":[107],"As":[108],"an":[109],"illustration,":[110],"method":[112],"applied":[114],"human":[118],"controller.":[119]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}