{"id":"https://openalex.org/W2165224827","doi":"https://doi.org/10.1109/robot.2008.4543721","title":"An approximate algorithm for solving oracular POMDPs","display_name":"An approximate algorithm for solving oracular POMDPs","publication_year":2008,"publication_date":"2008-05-01","ids":{"openalex":"https://openalex.org/W2165224827","doi":"https://doi.org/10.1109/robot.2008.4543721","mag":"2165224827"},"language":"en","primary_location":{"id":"doi:10.1109/robot.2008.4543721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2008.4543721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Robotics and Automation","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/A5015946460","display_name":"Nicholas Armstrong-Crews","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nicholas Armstrong-Crews","raw_affiliation_strings":["Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Robotics Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057963205","display_name":"Manuela Veloso","orcid":"https://orcid.org/0000-0002-1995-095X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manuela Veloso","raw_affiliation_strings":["Computer Science Department, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5015946460"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.12082124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3346","last_page":"3352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9995999932289124,"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":0.9995999932289124,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9966999888420105,"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":0.9929999709129333,"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/oracle","display_name":"Oracle","score":0.793720543384552},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7805396318435669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7367271780967712},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-process","display_name":"Partially observable Markov decision process","score":0.7069056034088135},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7031704187393188},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5845690369606018},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5783814191818237},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5697596073150635},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.49448394775390625},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.46176499128341675},{"id":"https://openalex.org/keywords/observable","display_name":"Observable","score":0.4442167580127716},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.433354914188385},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3683708906173706},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.3282734751701355},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.214369535446167},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.19668903946876526},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1894991099834442},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.12583929300308228}],"concepts":[{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.793720543384552},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7805396318435669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7367271780967712},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.7069056034088135},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7031704187393188},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5845690369606018},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5783814191818237},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5697596073150635},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49448394775390625},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.46176499128341675},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.4442167580127716},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.433354914188385},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3683708906173706},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3282734751701355},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.214369535446167},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.19668903946876526},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1894991099834442},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.12583929300308228},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/robot.2008.4543721","is_oa":false,"landing_page_url":"https://doi.org/10.1109/robot.2008.4543721","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Robotics and Automation","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.141.5595","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.141.5595","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/afs/cs/user/mmv/www/papers/08icra-nick.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1526144783","https://openalex.org/W1532688806","https://openalex.org/W1539216098","https://openalex.org/W1564812679","https://openalex.org/W1584530380","https://openalex.org/W2032100464","https://openalex.org/W2134802714","https://openalex.org/W2168024904","https://openalex.org/W2168359464","https://openalex.org/W2211790881","https://openalex.org/W2949773717","https://openalex.org/W6631864160","https://openalex.org/W6633952562","https://openalex.org/W6679977494","https://openalex.org/W6684620542"],"related_works":["https://openalex.org/W2999848267","https://openalex.org/W2096013579","https://openalex.org/W52153049","https://openalex.org/W1760611253","https://openalex.org/W1589140671","https://openalex.org/W1515117609","https://openalex.org/W4323315247","https://openalex.org/W131709709","https://openalex.org/W2294884454","https://openalex.org/W3169161914"],"abstract_inverted_index":{"We":[0,46],"propose":[1],"a":[2,21,43,80,126,168,204],"new":[3],"approximate":[4,158],"algorithm,":[5],"LA-":[6],"JIV":[7,49,85,97],"(lookahead":[8],"J-MDP":[9],"information":[10,41,51],"value),":[11],"to":[12,53,98,155,175],"solve":[13,54],"oracular":[14],"partially":[15],"observable":[16],"Markov":[17],"decision":[18],"problems":[19],"(OPOMDPs),":[20],"special":[22],"type":[23],"of":[24,63,71,78,116,122,178,203],"POMDP":[25,159],"that":[26,34,59,128,142,165,187],"rather":[27],"than":[28,191],"standard":[29],"observations":[30],"includes":[31],"an":[32,56,139,144,200],"\"oracle\"":[33],"can":[35],"be":[36],"consulted":[37],"for":[38],"full":[39],"state":[40,180],"at":[42,113],"fixed":[44],"cost.":[45],"previously":[47],"introduced":[48],"(J-MDP":[50],"value)":[52],"OPOMDPs,":[55],"heuristic":[57],"algorithm":[58,141],"utilizes":[60],"the":[61,64,69,73,76,89,107,114,123,150,176,179],"solution":[62],"underlying":[65],"MDP":[66],"and":[67,181],"weighs":[68],"value":[70,77],"consulting":[72],"oracle":[74],"against":[75],"taking":[79],"state-modifying":[81],"action.":[82],"While":[83],"efficient,":[84],"will":[86],"rarely":[87],"find":[88],"optimal":[90,108],"solution.":[91,147],"In":[92],"this":[93,130,135],"paper,":[94],"we":[95,137,163,194],"extend":[96],"include":[99],"lookahead,":[100],"thereby":[101,184],"permitting":[102],"arbitrarily":[103],"small":[104],"deviation":[105],"from":[106],"policy's":[109],"long-term":[110],"expected":[111],"reward":[112],"cost":[115],"added":[117],"computation":[118],"time.":[119],"The":[120],"depth":[121],"lookahead":[124],"is":[125,167],"parameter":[127],"governs":[129],"tradeoff;":[131],"by":[132],"iteratively":[133],"increasing":[134],"depth,":[136],"provide":[138],"anytime":[140],"yields":[143],"ever-":[145],"improving":[146],"LA-JIV":[148,166],"leverages":[149],"OPOMDP":[151,206],"framework's":[152],"unique":[153],"characteristics":[154],"outperform":[156],"general-purpose":[157],"solvers;":[160],"in":[161],"fact,":[162],"prove":[164],"poly-time":[169],"approximation":[170],"scheme":[171],"(PTAS)":[172],"with":[173],"respect":[174],"size":[177],"observation":[182],"spaces,":[183],"showing":[185],"rigorously":[186],"OPOMDPs":[188],"are":[189],"\"easier\"":[190],"POMDPs.":[192],"Finally,":[193],"substantiate":[195],"our":[196],"theoretical":[197],"results":[198],"via":[199],"empirical":[201],"analysis":[202],"benchmark":[205],"instance.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2013,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}