{"id":"https://openalex.org/W77538448","doi":"https://doi.org/10.48550/arxiv.1206.3263","title":"Sparse Stochastic Finite-State Controllers for POMDPs","display_name":"Sparse Stochastic Finite-State Controllers for POMDPs","publication_year":2012,"publication_date":"2012-06-13","ids":{"openalex":"https://openalex.org/W77538448","doi":"https://doi.org/10.48550/arxiv.1206.3263","mag":"77538448"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:1206.3263","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1206.3263","pdf_url":"https://arxiv.org/pdf/1206.3263","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1206.3263","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108501549","display_name":"Eric A. Hansen","orcid":"https://orcid.org/0000-0002-8445-2375","observed_orcids":["https://orcid.org/0000-0002-8445-2375"]},"institutions":[{"id":"https://openalex.org/I99041443","display_name":"Mississippi State University","ror":"https://ror.org/0432jq872","country_code":"US","type":"education","lineage":["https://openalex.org/I4210141039","https://openalex.org/I99041443"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hansen, Eric A.","raw_affiliation_strings":["Department of Computer Science and Engineering, Mississippi State University, Mississippi State MS#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Mississippi State University, Mississippi State MS#TAB#","institution_ids":["https://openalex.org/I99041443"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5108501549"],"corresponding_institution_ids":["https://openalex.org/I99041443"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"256","last_page":"263"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9843999743461609,"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":0.9843999743461609,"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":0.00989999994635582,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.0017000000225380063,"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":0.8960000276565552},{"id":"https://openalex.org/keywords/linear-programming","display_name":"linear programming","score":0.777999997138977},{"id":"https://openalex.org/keywords/policy-improvement","display_name":"policy improvement","score":0.7400000095367432},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.7609999775886536}],"concepts":[{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.6984347105026245},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.6837466359138489},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.6491825580596924},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.639356791973114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6361039280891418},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6358599662780762},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5853714942932129},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5544049739837646},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.5482107996940613},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.35269802808761597},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2592993974685669},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22950589656829834},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2184089720249176},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.1941397488117218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08873531222343445},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"pmh:oai:arXiv.org:1206.3263","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1206.3263","pdf_url":"https://arxiv.org/pdf/1206.3263","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.143.8789","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.143.8789","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://uai2008.cs.helsinki.fi/UAI_camera_ready/hansen.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.330.9153","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.330.9153","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.aaai.org/Papers/Workshops/2008/WS-08-01/WS08-01-006.pdf","raw_type":"text"},{"id":"doi:10.48550/arxiv.1206.3263","doi":"https://doi.org/10.48550/arxiv.1206.3263","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1206.3263","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"mag:77538448","doi":null,"is_oa":false,"landing_page_url":"https://www.aaai.org/Papers/Workshops/2008/WS-08-01/WS08-01-006.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306421103","display_name":"Uncertainty in Artificial Intelligence","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"Uncertainty in Artificial Intelligence","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1206.3263","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1206.3263","pdf_url":"https://arxiv.org/pdf/1206.3263","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W176675923","https://openalex.org/W1494689917","https://openalex.org/W1528120147","https://openalex.org/W1532688806","https://openalex.org/W1579579904","https://openalex.org/W1640774615","https://openalex.org/W1701684472","https://openalex.org/W1762430620","https://openalex.org/W2101984404","https://openalex.org/W2103614073","https://openalex.org/W2144283793","https://openalex.org/W2168359464","https://openalex.org/W3103182070"],"related_works":["https://openalex.org/W1579579904","https://openalex.org/W125990855","https://openalex.org/W2109393574","https://openalex.org/W2168359464","https://openalex.org/W2144283793","https://openalex.org/W2148864095","https://openalex.org/W162215616","https://openalex.org/W2168762208","https://openalex.org/W2103541323","https://openalex.org/W3166934405","https://openalex.org/W3023657089","https://openalex.org/W2088147131","https://openalex.org/W2523642882","https://openalex.org/W2004597074","https://openalex.org/W223326216","https://openalex.org/W2292613520","https://openalex.org/W1974307281","https://openalex.org/W1503109067","https://openalex.org/W2804200087","https://openalex.org/W2219400200"],"abstract_inverted_index":{"Bounded":[0],"policy":[1,47,103,121],"iteration":[2,104],"is":[3,79],"an":[4],"approach":[5],"to":[6],"solving":[7],"infinite-horizon":[8],"POMDPs":[9],"that":[10,105],"represents":[11],"policies":[12],"as":[13,126],"stochastic":[14,112],"finite-state":[15,113],"controllers":[16],"and":[17,42,83],"iteratively":[18],"improves":[19,119],"a":[20,74,99,111,120],"controller":[21],"by":[22,122],"adjusting":[23],"the":[24,33,36,39,44,51,61,64,69,88,91,107,123,127],"parameters":[25,54,72],"of":[26,38,46,53,55,63,71,73,90,101,110],"each":[27,56,116],"node":[28,75],"using":[29],"linear":[30,40],"programming.":[31],"In":[32,115],"original":[34,128],"algorithm,":[35,129],"size":[37,62,89],"programs,":[41],"thus":[43],"complexity":[45],"improvement,":[48],"depends":[49],"on":[50,94],"number":[52,70],"node,":[57],"which":[58],"grows":[59],"with":[60,76,87,131],"controller.":[65,92,114],"But":[66],"in":[67],"practice,":[68],"non-zero":[77],"values":[78],"often":[80],"very":[81],"small,":[82],"does":[84],"not":[85],"grow":[86],"Based":[93],"this":[95],"observation,":[96],"we":[97],"develop":[98],"version":[100],"bounded":[102],"leverages":[106],"sparse":[108],"structure":[109],"iteration,":[117],"it":[118],"same":[124],"amount":[125],"but":[130],"much":[132],"better":[133],"scalability.":[134]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2025-10-10T00:00:00"}