{"id":"https://openalex.org/W3139984405","doi":"https://doi.org/10.1109/wsc.2011.6147989","title":"Stochastic policy search for variance-penalized semi-Markov control","display_name":"Stochastic policy search for variance-penalized semi-Markov control","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W3139984405","doi":"https://doi.org/10.1109/wsc.2011.6147989","mag":"3139984405"},"language":"en","primary_location":{"id":"doi:10.1109/wsc.2011.6147989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc.2011.6147989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 Winter Simulation Conference (WSC)","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/A5053889549","display_name":"Abhijit Gosavi","orcid":"https://orcid.org/0000-0002-9703-4076"},"institutions":[{"id":"https://openalex.org/I20382870","display_name":"Missouri University of Science and Technology","ror":"https://ror.org/00scwqd12","country_code":"US","type":"education","lineage":["https://openalex.org/I20382870"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Abhijit Gosavi","raw_affiliation_strings":["219 Engineering Management, Missouri University of Science and Technology, Rolla, MO, USA"],"affiliations":[{"raw_affiliation_string":"219 Engineering Management, Missouri University of Science and Technology, Rolla, MO, USA","institution_ids":["https://openalex.org/I20382870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052264378","display_name":"Mandar Purohit","orcid":null},"institutions":[{"id":"https://openalex.org/I1292842697","display_name":"Environmental Systems Research Institute (United States)","ror":"https://ror.org/0428exr50","country_code":"US","type":"company","lineage":["https://openalex.org/I1292842697"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mandar Purohit","raw_affiliation_strings":["ESRI, Redlands, CA, USA"],"affiliations":[{"raw_affiliation_string":"ESRI, Redlands, CA, USA","institution_ids":["https://openalex.org/I1292842697"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5053889549"],"corresponding_institution_ids":["https://openalex.org/I20382870"],"apc_list":null,"apc_paid":null,"fwci":0.3138,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.65479064,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"7","issue":null,"first_page":"2860","last_page":"2871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9986000061035156,"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"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9986000061035156,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9972000122070312,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9965999722480774,"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/markov-decision-process","display_name":"Markov decision process","score":0.7875474691390991},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.718810498714447},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.6289196610450745},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5896078944206238},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5804038047790527},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.5381925702095032},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.48682159185409546},{"id":"https://openalex.org/keywords/variable-order-markov-model","display_name":"Variable-order Markov model","score":0.4625531733036041},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4389561712741852},{"id":"https://openalex.org/keywords/markov-model","display_name":"Markov model","score":0.3761201500892639},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3199915289878845},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.20858103036880493},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1307092308998108},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.09809735417366028}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7875474691390991},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.718810498714447},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.6289196610450745},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5896078944206238},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5804038047790527},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5381925702095032},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.48682159185409546},{"id":"https://openalex.org/C54907487","wikidata":"https://www.wikidata.org/wiki/Q7915688","display_name":"Variable-order Markov model","level":4,"score":0.4625531733036041},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4389561712741852},{"id":"https://openalex.org/C163836022","wikidata":"https://www.wikidata.org/wiki/Q6771326","display_name":"Markov model","level":3,"score":0.3761201500892639},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3199915289878845},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.20858103036880493},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1307092308998108},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.09809735417366028},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/wsc.2011.6147989","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wsc.2011.6147989","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2011 Winter Simulation Conference (WSC)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.416.1979","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.416.1979","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.informs-sim.org/wsc11papers/255.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"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":25,"referenced_works":["https://openalex.org/W134786152","https://openalex.org/W203276351","https://openalex.org/W1538558539","https://openalex.org/W2024786776","https://openalex.org/W2057510529","https://openalex.org/W2098432798","https://openalex.org/W2100857832","https://openalex.org/W2101130101","https://openalex.org/W2104130615","https://openalex.org/W2106216878","https://openalex.org/W2117428849","https://openalex.org/W2124289529","https://openalex.org/W2128661050","https://openalex.org/W2144446635","https://openalex.org/W2169206416","https://openalex.org/W2169293926","https://openalex.org/W2494547223","https://openalex.org/W2587326475","https://openalex.org/W2752779325","https://openalex.org/W3125893104","https://openalex.org/W3141902362","https://openalex.org/W3147321350","https://openalex.org/W6677435986","https://openalex.org/W6733393097","https://openalex.org/W6807091881"],"related_works":["https://openalex.org/W2027903142","https://openalex.org/W3166133680","https://openalex.org/W2989366387","https://openalex.org/W2592341669","https://openalex.org/W2794873331","https://openalex.org/W2075517632","https://openalex.org/W2735859191","https://openalex.org/W2376290921","https://openalex.org/W4252142810","https://openalex.org/W2387462590"],"abstract_inverted_index":{"The":[0],"variance-penalized":[1],"metric":[2,32],"in":[3,33,51,59,75,87],"Markov":[4,99],"decision":[5,39],"processes":[6],"(MDPs)":[7],"seeks":[8],"to":[9,28,116],"maximize":[10],"the":[11,18,30,34,37,43,46,48,71,76,81,89,93,98,103,118,133,136],"average":[12],"reward":[13],"minus":[14],"a":[15,62],"scalar":[16],"times":[17],"variance":[19,72],"of":[20,36,73,97,105,135],"rewards.":[21],"In":[22,42],"this":[23],"paper,":[24],"our":[25],"goal":[26],"is":[27,54,86],"study":[29],"same":[31],"context":[35],"semi-Markov":[38],"process":[40],"(SMDP).":[41],"SMDP,":[44],"unlike":[45],"MDP,":[47],"time":[49],"spent":[50],"each":[52],"transition":[53,95,137],"not":[55],"identical":[56],"and":[57,78,113,125],"may":[58],"fact":[60],"be":[61,127],"random":[63],"variable.":[64],"We":[65,101],"first":[66],"develop":[67],"an":[68],"expression":[69],"for":[70],"rewards":[74],"SMDPs,":[77],"then":[79],"formulate":[80],"VP-SMDP.":[82],"Our":[83],"interest":[84],"here":[85],"solving":[88],"problem":[90],"without":[91],"generating":[92],"underlying":[94],"probabilities":[96],"chains.":[100],"propose":[102],"use":[104,122],"two":[106],"stochastic":[107,123],"search":[108],"techniques,":[109],"namely":[110],"simultaneous":[111],"perturbation":[112],"learning":[114],"automata,":[115],"solve":[117],"problem;":[119],"these":[120],"techniques":[121],"policies":[124],"can":[126],"used":[128],"within":[129],"simulators,":[130],"thereby":[131],"avoiding":[132],"generation":[134],"probabilities.":[138]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}