{"id":"https://openalex.org/W2135290313","doi":"https://doi.org/10.1109/adprl.2009.4927536","title":"Algorithms for variance reduction in a policy-gradient based actor-critic framework","display_name":"Algorithms for variance reduction in a policy-gradient based actor-critic framework","publication_year":2009,"publication_date":"2009-03-01","ids":{"openalex":"https://openalex.org/W2135290313","doi":"https://doi.org/10.1109/adprl.2009.4927536","mag":"2135290313"},"language":"en","primary_location":{"id":"doi:10.1109/adprl.2009.4927536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","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/A5021845994","display_name":"Yogesh P. Awate","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117535","display_name":"Cognizant (India)","ror":"https://ror.org/01x51st25","country_code":"IN","type":"company","lineage":["https://openalex.org/I163361683","https://openalex.org/I4210117535"]},{"id":"https://openalex.org/I162827531","display_name":"Indian Institute of Technology Bombay","ror":"https://ror.org/02qyf5152","country_code":"IN","type":"education","lineage":["https://openalex.org/I162827531"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Yogesh P. Awate","raw_affiliation_strings":["Department of Industrial Engineering and Operations Research, Indian Institute of Technology, Bombay, India","marketRx - A Cognizant Company, Gurgaon, India - 122002"],"affiliations":[{"raw_affiliation_string":"Department of Industrial Engineering and Operations Research, Indian Institute of Technology, Bombay, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"marketRx - A Cognizant Company, Gurgaon, India - 122002","institution_ids":["https://openalex.org/I4210117535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5021845994"],"corresponding_institution_ids":["https://openalex.org/I162827531","https://openalex.org/I4210117535"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13082344,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"12","issue":null,"first_page":"130","last_page":"136"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9993000030517578,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9728999733924866,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/estimator","display_name":"Estimator","score":0.6734637022018433},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5552220940589905},{"id":"https://openalex.org/keywords/variance-reduction","display_name":"Variance reduction","score":0.5432272553443909},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5412326455116272},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5021114349365234},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4901019036769867},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.4226798713207245},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.42184603214263916},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4210259020328522},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.41537028551101685},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4127841889858246},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4099541902542114},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.21350175142288208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18251970410346985},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09794667363166809}],"concepts":[{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6734637022018433},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5552220940589905},{"id":"https://openalex.org/C62644790","wikidata":"https://www.wikidata.org/wiki/Q3454689","display_name":"Variance reduction","level":3,"score":0.5432272553443909},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5412326455116272},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5021114349365234},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4901019036769867},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.4226798713207245},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.42184603214263916},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4210259020328522},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.41537028551101685},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4127841889858246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4099541902542114},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.21350175142288208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18251970410346985},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09794667363166809},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/adprl.2009.4927536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/adprl.2009.4927536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1576452626","https://openalex.org/W1646707810","https://openalex.org/W1970789124","https://openalex.org/W2009303086","https://openalex.org/W2094364653","https://openalex.org/W2108682071","https://openalex.org/W2114537044","https://openalex.org/W2120465407","https://openalex.org/W2124098876","https://openalex.org/W2130801532","https://openalex.org/W2136602922","https://openalex.org/W2144446635","https://openalex.org/W2155027007","https://openalex.org/W2246213791","https://openalex.org/W2400458653","https://openalex.org/W3103182070","https://openalex.org/W6676023451","https://openalex.org/W6677049199","https://openalex.org/W6679257226","https://openalex.org/W6680194329","https://openalex.org/W6683204974"],"related_works":["https://openalex.org/W2111181341","https://openalex.org/W2886060011","https://openalex.org/W363903320","https://openalex.org/W2313927419","https://openalex.org/W4253934505","https://openalex.org/W2387727280","https://openalex.org/W2886934452","https://openalex.org/W1489099099","https://openalex.org/W2024369332","https://openalex.org/W2981958474"],"abstract_inverted_index":{"We":[0,78,107,123,148],"consider":[1],"the":[2,17,60,97,104,115,130,142,163,167],"framework":[3],"of":[4,7,59,87],"a":[5,73,80,100,109,150],"set":[6],"recently":[8],"proposed":[9,164],"two-timescale":[10],"actor-critic":[11],"algorithms":[12,46,165],"for":[13,67,84,119,133,154],"reinforcement-learning":[14],"(RL)":[15],"using":[16,129],"long-run":[18],"average-reward":[19],"criterion":[20],"and":[21,28,37,90],"linear":[22],"feature-based":[23],"value-function":[24,51],"approximation.":[25,147],"The":[26,158],"actor":[27,111,127],"critic":[29,76],"updates":[30],"are":[31],"based":[32,113],"on":[33,114,169],"stochastic":[34],"policy-gradient":[35,61,136,143],"ascent":[36],"temporal-difference":[38],"algorithms,":[39,44],"respectively.":[40],"Unlike":[41],"conventional":[42],"RL":[43],"policy-gradient-based":[45],"guarantee":[47],"convergence":[48],"even":[49],"with":[50,145],"approximation":[52],"but":[53],"suffer":[54],"due":[55],"to":[56],"high":[57],"variance":[58,66,85],"estimator.":[62],"To":[63],"minimize":[64],"this":[65],"an":[68,88,92,120,134,155],"existing":[69,121,156],"algorithm,":[70],"we":[71,139],"derive":[72,91,108,124],"stochastic-gradient-based":[74],"novel":[75,81,110,126,151],"update.":[77],"propose":[79],"baseline":[82,94,117,132],"structure":[83],"minimization":[86],"estimator":[89,137],"optimal":[93,116,131],"which":[95,138],"makes":[96],"covariance":[98],"matrix":[99,102],"zero":[101],"-":[103],"best":[105],"achievable.":[106],"update":[112,128],"deduced":[118],"algorithm.":[122,157],"another":[125],"unbiased":[135],"deduce":[140],"from":[141],"theorem":[144],"function":[146],"obtain":[149],"variance-minimization-based":[152],"interpretation":[153],"computational":[159],"results":[160],"demonstrate":[161],"that":[162],"outperform":[166],"state-of-the-art":[168],"Garnet":[170],"problems.":[171]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}