乐胖代购免代理版

{"id":"https://openalex.org/W2126330148","doi":"https://doi.org/10.1109/acc.2006.1656451","title":"Importance sampling actor-critic algorithms","display_name":"Importance sampling actor-critic algorithms","publication_year":2006,"publication_date":"2006-01-01","ids":{"openalex":"https://openalex.org/W2126330148","doi":"https://doi.org/10.1109/acc.2006.1656451","mag":"2126330148"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2006.1656451","pdf_url":null,"source":{"id":"https://openalex.org/S4306417662","display_name":"American Control Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://people.csail.mit.edu/~fisher/publications/papers/WilFis06acc.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5076006629","display_name":"Jason Williams","orcid":"https://orcid.org/0000-0002-2416-075X"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.L. Williams","raw_affiliation_strings":["[Lab. for Inf. & Decision Syst., Massachusetts Inst. of Technol., Cambridge, MA]"],"affiliations":[{"raw_affiliation_string":"[Lab. for Inf. & Decision Syst., Massachusetts Inst. of Technol., Cambridge, MA]","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091608832","display_name":"John W. Fisher","orcid":"https://orcid.org/0000-0003-4844-3495"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.W. Fisher","raw_affiliation_strings":["[Lab. for Inf. & Decision Syst., Massachusetts Inst. of Technol., Cambridge, MA]"],"affiliations":[{"raw_affiliation_string":"[Lab. for Inf. & Decision Syst., Massachusetts Inst. of Technol., Cambridge, MA]","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107833743","display_name":"Alan S. Willsky","orcid":null},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"A.S. Willsky","raw_affiliation_strings":["[Lab. for Inf. & Decision Syst., Massachusetts Inst. of Technol., Cambridge, MA]"],"affiliations":[{"raw_affiliation_string":"[Lab. for Inf. & Decision Syst., Massachusetts Inst. of Technol., Cambridge, MA]","institution_ids":["https://openalex.org/I63966007"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.834,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":8,"citation_normalized_percentile":{"value":0.648172,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":80,"max":81},"biblio":{"volume":"13","issue":null,"first_page":"6 pp.","last_page":"6 pp."},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9966,"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":0.9966,"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":0.9724,"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/T10409","display_name":"Fuel Cells and Related Materials","score":0.9712,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/variance-reduction","display_name":"Variance reduction","score":0.72632587}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.73647296},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.72632587},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.69937515},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.64750683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6081092},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.5961765},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5815185},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.55500233},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.49450633},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44983324},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44363314},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.43863818},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30531996},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22548404},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2006.1656451","pdf_url":null,"source":{"id":"https://openalex.org/S4306417662","display_name":"American Control Conference","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":false},{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.131.4221","pdf_url":"http://people.csail.mit.edu/~fisher/publications/papers/WilFis06acc.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.131.4221","pdf_url":"http://people.csail.mit.edu/~fisher/publications/papers/WilFis06acc.pdf","source":{"id":"https://openalex.org/S4306400349","display_name":"CiteSeer X (The Pennsylvania State University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I130769515","host_organization_name":"Pennsylvania State University","host_organization_lineage":["https://openalex.org/I130769515"],"host_organization_lineage_names":["Pennsylvania State University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":7,"referenced_works":["https://openalex.org/W1507222174","https://openalex.org/W1518539242","https://openalex.org/W2009303086","https://openalex.org/W2098432798","https://openalex.org/W2139418546","https://openalex.org/W2253356247","https://openalex.org/W2950849043"],"related_works":["https://openalex.org/W363903320","https://openalex.org/W2951368390","https://openalex.org/W2376074353","https://openalex.org/W2298254442","https://openalex.org/W2169816622","https://openalex.org/W2169367269","https://openalex.org/W2103055865","https://openalex.org/W2039667440","https://openalex.org/W2010899721","https://openalex.org/W1997242758"],"abstract_inverted_index":{"Importance":[0],"sampling":[1],"(IS)":[2],"and":[3],"actor-critic":[4],"are":[5],"two":[6],"methods":[7,34],"which":[8],"have":[9],"been":[10],"used":[11,30],"to":[12,35,61],"reduce":[13],"the":[14,45,81],"variance":[15,79],"of":[16,48,94],"gradient":[17,21,63,68,100],"estimates":[18,64],"in":[19,65,78,90,96],"policy":[20,43,67],"optimization":[22],"methods.":[23],"We":[24],"show":[25],"how":[26],"IS":[27,82],"can":[28],"be":[29],"with":[31],"temporal":[32],"difference":[33],"estimate":[36],"a":[37,66,74,91,99],"cost":[38],"function":[39],"parameter":[40],"for":[41,84,98],"one":[42],"using":[44],"entire":[46],"history":[47],"system":[49],"interactions":[50],"incorporating":[51],"many":[52],"different":[53],"policies.":[54],"The":[55,70],"resulting":[56,89],"algorithm":[57],"is":[58],"then":[59],"applied":[60],"improving":[62],"optimization.":[69],"empirical":[71],"results":[72],"demonstrate":[73],"20-40":[75],"times":[76],"reduction":[77],"over":[80],"estimator":[83],"an":[85],"example":[86],"queueing":[87],"problem,":[88],"similar":[92],"factor":[93],"improvement":[95],"convergence":[97],"search":[101]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2126330148","counts_by_year":[{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2024-12-10T11:42:00.909489","created_date":"2016-06-24"}