{"id":"https://openalex.org/W2150439808","doi":"https://doi.org/10.1109/allerton.2010.5707072","title":"Approximate dynamic programming with correlated Bayesian beliefs","display_name":"Approximate dynamic programming with correlated Bayesian beliefs","publication_year":2010,"publication_date":"2010-09-01","ids":{"openalex":"https://openalex.org/W2150439808","doi":"https://doi.org/10.1109/allerton.2010.5707072","mag":"2150439808"},"language":"en","primary_location":{"id":"doi:10.1109/allerton.2010.5707072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2010.5707072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-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/A5044367354","display_name":"Ilya O. Ryzhov","orcid":"https://orcid.org/0000-0002-4191-084X"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ilya O. Ryzhov","raw_affiliation_strings":["Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054833334","display_name":"Warren B. Powell","orcid":"https://orcid.org/0000-0002-4364-7555"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Warren B. Powell","raw_affiliation_strings":["Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5044367354"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":2.3225,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90095201,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"9","issue":null,"first_page":"1360","last_page":"1367"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9864000082015991,"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":0.9864000082015991,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9861999750137329,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10969","display_name":"Water resources management and optimization","score":0.9857000112533569,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.8190187215805054},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7073881030082703},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6472411751747131},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.6171911358833313},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5810582041740417},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5252423286437988},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5093165636062622},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45029565691947937},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.43287044763565063},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4240327477455139},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4148932993412018},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28678643703460693},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18380782008171082}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.8190187215805054},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7073881030082703},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6472411751747131},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.6171911358833313},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5810582041740417},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5252423286437988},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5093165636062622},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45029565691947937},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.43287044763565063},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4240327477455139},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4148932993412018},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28678643703460693},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18380782008171082},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/allerton.2010.5707072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/allerton.2010.5707072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.252.7042","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.252.7042","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://optimallearning.princeton.edu/Papers/RyzhovPowell-kgdp_AllertonconferenceJune142010.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.300.1674","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.300.1674","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.castlelab.princeton.edu/Papers/RyzhovPowell-kgdp_AllertonconferenceJune122010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W295994756","https://openalex.org/W1496855202","https://openalex.org/W1499021337","https://openalex.org/W1552132860","https://openalex.org/W1576452626","https://openalex.org/W1582436621","https://openalex.org/W1591803298","https://openalex.org/W1601081659","https://openalex.org/W1931792391","https://openalex.org/W1965288387","https://openalex.org/W2006258746","https://openalex.org/W2039521867","https://openalex.org/W2069034916","https://openalex.org/W2072302356","https://openalex.org/W2089425220","https://openalex.org/W2108692343","https://openalex.org/W2116459397","https://openalex.org/W2116686327","https://openalex.org/W2128775537","https://openalex.org/W2132849848","https://openalex.org/W2141186877","https://openalex.org/W2155927283","https://openalex.org/W2156974606","https://openalex.org/W2165951235","https://openalex.org/W2312609093","https://openalex.org/W2317700292","https://openalex.org/W2334782222","https://openalex.org/W2341171179","https://openalex.org/W2400458653","https://openalex.org/W2487144912","https://openalex.org/W2797328151","https://openalex.org/W2911283634","https://openalex.org/W2914656440","https://openalex.org/W3023939952","https://openalex.org/W4214499292","https://openalex.org/W4300553073","https://openalex.org/W6610408509","https://openalex.org/W6629610187","https://openalex.org/W6629614444","https://openalex.org/W6634528131","https://openalex.org/W6634907821","https://openalex.org/W6660491549","https://openalex.org/W6667579268","https://openalex.org/W6677241066","https://openalex.org/W6679295095","https://openalex.org/W6679599195","https://openalex.org/W6689723076","https://openalex.org/W6704298589","https://openalex.org/W6722065765","https://openalex.org/W6724046077","https://openalex.org/W7018273120"],"related_works":["https://openalex.org/W4255265352","https://openalex.org/W4239477580","https://openalex.org/W4285537323","https://openalex.org/W1932159282","https://openalex.org/W2090698372","https://openalex.org/W4383890581","https://openalex.org/W2965004901","https://openalex.org/W2921905705","https://openalex.org/W4233178034","https://openalex.org/W2003293420"],"abstract_inverted_index":{"In":[0],"approximate":[1],"dynamic":[2],"programming,":[3],"we":[4],"can":[5,28],"represent":[6],"our":[7],"uncertainty":[8],"about":[9,33],"the":[10,51,56,63],"value":[11],"function":[12],"using":[13],"a":[14,21,25,45],"Bayesian":[15],"model":[16],"with":[17,31],"correlated":[18,69],"beliefs.":[19],"Thus,":[20],"decision":[22],"made":[23],"at":[24],"single":[26],"state":[27],"provide":[29],"us":[30],"information":[32],"many":[34],"states,":[35],"making":[36],"each":[37],"individual":[38],"observation":[39],"much":[40],"more":[41],"powerful.":[42],"We":[43],"propose":[44],"new":[46],"exploration":[47],"strategy":[48],"based":[49],"on":[50,83],"knowledge":[52],"gradient":[53],"concept":[54],"from":[55],"optimal":[57],"learning":[58],"literature,":[59],"which":[60],"is":[61],"currently":[62],"only":[64],"method":[65,74],"capable":[66],"of":[67],"handling":[68],"belief":[70],"structures.":[71],"The":[72],"proposed":[73],"outperforms":[75],"several":[76],"other":[77],"heuristics":[78],"in":[79],"numerical":[80],"experiments":[81],"conducted":[82],"two":[84],"broad":[85],"problem":[86],"classes.":[87]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}