{"id":"https://openalex.org/W7095911290","doi":null,"title":"EXACT AND APPROXIMATE ALGORITHMS FOR PARTIALLY OBSERVABLE MARKOV DECISION PROCESSES","display_name":"EXACT AND APPROXIMATE ALGORITHMS FOR PARTIALLY OBSERVABLE MARKOV DECISION PROCESSES","alternate_titles":[],"publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W7095911290"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.1377","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.1377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.brown.edu/research/ai/pomdp/papers/thesis-dbl.ps.gz","raw_type":"text"},"parent_works":[],"lineage":["https://openalex.org/W7095911290"],"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/A5023048350","display_name":"Anthony R. Cassandra","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"contributor_roles":[],"raw_author_name":"Anthony Rocco Cassandra","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5023048350"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":8,"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":0.9535999894142151,"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":0.9535999894142151,"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":0.02979999966919422,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.0012000000569969416,"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-processes","display_name":"partially observable Markov decision processes","score":0.9990000128746033},{"id":"https://openalex.org/keywords/optimal-policy-computation","display_name":"optimal policy computation","score":0.7549999952316284},{"id":"https://openalex.org/keywords/sequential-decision-making","display_name":"sequential decision making","score":0.7400000095367432},{"id":"https://openalex.org/keywords/pspace-completeness","display_name":"PSPACE-completeness","score":0.871999979019165},{"id":"https://openalex.org/keywords/np-completeness","display_name":"NP-completeness","score":0.8399999737739563},{"id":"https://openalex.org/keywords/exact-algorithms","display_name":"exact algorithms","score":0.8289999961853027},{"id":"https://openalex.org/keywords/suboptimal-control","display_name":"suboptimal control","score":0.8659999966621399}],"concepts":[{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.8593999743461609},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7778000235557556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6402000188827515},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5393999814987183},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.538100004196167},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.4814999997615814},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.47130000591278076},{"id":"https://openalex.org/C150325174","wikidata":"https://www.wikidata.org/wiki/Q4335500","display_name":"Optimal decision","level":3,"score":0.4596000015735626},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.4453999996185303},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4343000054359436},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3986999988555908},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C115988155","wikidata":"https://www.wikidata.org/wiki/Q3262192","display_name":"Decision problem","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C2984634286","wikidata":"https://www.wikidata.org/wiki/Q1331926","display_name":"Decision process","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C20837028","wikidata":"https://www.wikidata.org/wiki/Q623966","display_name":"Influence diagram","level":3,"score":0.3061000108718872},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.28839999437332153},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28459998965263367},{"id":"https://openalex.org/C186116695","wikidata":"https://www.wikidata.org/wiki/Q5249226","display_name":"Decision analysis","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2547000050544739},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C59594135","wikidata":"https://www.wikidata.org/wiki/Q5249242","display_name":"Decision model","level":2,"score":0.25110000371932983}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.71.1377","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.71.1377","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.brown.edu/research/ai/pomdp/papers/thesis-dbl.ps.gz","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/W2099873296","https://openalex.org/W7096835626","https://openalex.org/W2065087844","https://openalex.org/W7095232061","https://openalex.org/W1558845053","https://openalex.org/W1679945064","https://openalex.org/W7096894209","https://openalex.org/W7099722445","https://openalex.org/W131709709","https://openalex.org/W7099907428"],"abstract_inverted_index":{"Automated":[0],"sequential":[1,52],"decision":[2,27,53,84],"making":[3,54],"is":[4,69,114,165],"crucial":[5],"in":[6,55,64,100],"many":[7],"contexts.":[8],"In":[9,46],"the":[10,22,39,41,58,66,111,118,128,158,176],"face":[11],"of":[12,35,122,185,202],"uncertainty,":[13],"this":[14,47],"task":[15],"becomes":[16,29,43],"even":[17],"more":[18,30,33],"important,":[19],"though":[20],"at":[21,51],"same":[23],"time,":[24],"computing":[25,92,157],"optimal":[26,94,112,129,159,177],"policies":[28,97,189],"complex.":[31],"The":[32],"sources":[34],"uncertainty":[36],"there":[37],"are,":[38],"harder":[40],"problem":[42],"to":[44,171,175],"solve.":[45],"work,":[48],"we":[49,181],"look":[50],"environments":[56],"where":[57],"actions":[59],"have":[60],"probabilistic":[61],"outcomes":[62],"and":[63,87,95,120,146,152,194],"which":[65,90],"system":[67],"state":[68],"only":[70],"partially":[71,81],"observable.":[72],"We":[73,141],"focus":[74],"on":[75,199],"using":[76,106],"a":[77,80,136,183,200],"model":[78],"called":[79],"observable":[82],"Markov":[83],"process":[85],"(POMDP)":[86],"explore":[88,196],"algorithms":[89,124],"address":[91],"both":[93],"approximate":[96,139],"for":[98,110,138,149,156,179,187],"use":[99],"controlling":[101],"processes":[102],"that":[103,190],"are":[104],"modeled":[105],"POMDPs.":[107],"Although":[108],"solving":[109],"policy":[113,161],"PSPACE-complete":[115],"(or":[116],"worse),":[117],"study":[119],"improvements":[121],"exact":[123],"lends":[125],"insight":[126],"into":[127],"solution":[130,178],"structure":[131],"as":[132,134],"well":[133],"providing":[135],"basis":[137],"solutions.":[140],"present":[142],"some":[143,150,153],"improvements,":[144],"analysis":[145],"empirical":[147],"comparisons":[148],"existing":[151],"novel":[154],"approaches":[155,186,205],"POMDP":[160],"exactly.":[162],"Since":[163],"it":[164],"also":[166],"hard":[167],"(NP-complete":[168],"or":[169],"worse)":[170],"derive":[172],"close":[173],"approximations":[174],"POMDPs,":[180],"consider":[182],"number":[184],"deriving":[188],"yield":[191],"sub-optimal":[192],"control":[193],"empirically":[195],"their":[197],"performance":[198],"range":[201],"problems.":[203],"These":[204]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7095911290","counts_by_year":[{"year":2014,"cited_by_count":2}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2025-10-27T00:00:00"}
