{"id":"https://openalex.org/W2059486486","doi":"https://doi.org/10.1109/cdc.2014.7039948","title":"An actor critic algorithm based on Grassmanian search","display_name":"An actor critic algorithm based on Grassmanian search","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2059486486","doi":"https://doi.org/10.1109/cdc.2014.7039948","mag":"2059486486"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2014.7039948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7039948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"53rd IEEE Conference on Decision and Control","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/A5103452758","display_name":"Prabuchandran K.J.","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Prabuchandran K.J.","raw_affiliation_strings":["Department of Computer Science and Automation, Indian Institute of Science, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038163398","display_name":"Shalabh Bhatnagar","orcid":"https://orcid.org/0000-0001-7644-3914"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shalabh Bhatnagar","raw_affiliation_strings":["Department of Computer Science and Automation, Indian Institute of Science, India","Department of Computer Science and Automation, Indian Institute of Science, Bangalore 560012, INDIA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bangalore 560012, INDIA","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018541798","display_name":"Vivek S. Borkar","orcid":"https://orcid.org/0000-0003-0756-5402"},"institutions":[{"id":"https://openalex.org/I64295750","display_name":"Indian Institute of Technology Indore","ror":"https://ror.org/01hhf7w52","country_code":"IN","type":"education","lineage":["https://openalex.org/I64295750"]},{"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":false,"raw_author_name":"Vivek S. Borkar","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology, Mumbai, India","Department of Electrical Engineering, Indian Institute of Technology, Mumbai, Powai-400076, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]},{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology, Mumbai, Powai-400076, India","institution_ids":["https://openalex.org/I64295750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103452758"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.409,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.74265095,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"13","issue":null,"first_page":"3597","last_page":"3602"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9975000023841858,"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":0.9975000023841858,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9947999715805054,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11195","display_name":"Simulation Techniques and Applications","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.6764646172523499},{"id":"https://openalex.org/keywords/simultaneous-perturbation-stochastic-approximation","display_name":"Simultaneous perturbation stochastic approximation","score":0.6310147047042847},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.6263049840927124},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6133937239646912},{"id":"https://openalex.org/keywords/gradient-descent","display_name":"Gradient descent","score":0.5703551769256592},{"id":"https://openalex.org/keywords/basis-function","display_name":"Basis function","score":0.5141282677650452},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.49492162466049194},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.47649329900741577},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.43220779299736023},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.43187829852104187},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4242261052131653},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4239587187767029},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.41828474402427673},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.41171106696128845},{"id":"https://openalex.org/keywords/gradient-method","display_name":"Gradient method","score":0.4104786515235901},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4053579270839691},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.3200927972793579},{"id":"https://openalex.org/keywords/stochastic-process","display_name":"Stochastic process","score":0.26318052411079407},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2245798408985138},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.171105295419693},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.11030644178390503}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6764646172523499},{"id":"https://openalex.org/C2779880469","wikidata":"https://www.wikidata.org/wiki/Q17084424","display_name":"Simultaneous perturbation stochastic approximation","level":3,"score":0.6310147047042847},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.6263049840927124},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6133937239646912},{"id":"https://openalex.org/C153258448","wikidata":"https://www.wikidata.org/wiki/Q1199743","display_name":"Gradient descent","level":3,"score":0.5703551769256592},{"id":"https://openalex.org/C5917680","wikidata":"https://www.wikidata.org/wiki/Q2621825","display_name":"Basis function","level":2,"score":0.5141282677650452},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.49492162466049194},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.47649329900741577},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.43220779299736023},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.43187829852104187},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4242261052131653},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4239587187767029},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.41828474402427673},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.41171106696128845},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.4104786515235901},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4053579270839691},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.3200927972793579},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.26318052411079407},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2245798408985138},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.171105295419693},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.11030644178390503},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2014.7039948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7039948","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"53rd IEEE Conference on Decision and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7900000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W359561291","https://openalex.org/W594357522","https://openalex.org/W1646707810","https://openalex.org/W1828381662","https://openalex.org/W1993704541","https://openalex.org/W1998172110","https://openalex.org/W2011233848","https://openalex.org/W2045512849","https://openalex.org/W2094364653","https://openalex.org/W2094387729","https://openalex.org/W2120465407","https://openalex.org/W2124289529","https://openalex.org/W2139418546","https://openalex.org/W2153267861","https://openalex.org/W2156737235","https://openalex.org/W2161270100","https://openalex.org/W2493209382","https://openalex.org/W2548880252","https://openalex.org/W2586680856","https://openalex.org/W4238852866","https://openalex.org/W4285719527","https://openalex.org/W6683195989"],"related_works":["https://openalex.org/W2038213655","https://openalex.org/W2079907724","https://openalex.org/W2546134129","https://openalex.org/W2169111093","https://openalex.org/W4382936136","https://openalex.org/W2104712676","https://openalex.org/W2118205332","https://openalex.org/W1973158011","https://openalex.org/W2885971921","https://openalex.org/W4387970357"],"abstract_inverted_index":{"We":[0,29,189,207],"propose":[1],"the":[2,24,32,35,38,42,50,75,92,95,99,103,107,111,118,137,149,163,172,184,194,229,234],"first":[3],"online":[4],"actor-critic":[5],"scheme":[6,170,232],"with":[7],"adaptive":[8],"basis":[9,100],"to":[10,87,105,147,202],"find":[11],"a":[12,18,79,167,177,203,217],"local":[13],"optimal":[14],"control":[15,123,200],"policy":[16,33,53],"for":[17,233],"Markov":[19],"Decision":[20],"Process":[21],"(MDP)":[22],"under":[23],"weighted":[25],"discounted":[26],"cost":[27],"objective.":[28,84],"parameterize":[30],"both":[31],"in":[34,41,49,117,162,183,226],"actor":[36,45,132],"and":[37],"value":[39,69,93,112,150],"function":[40,70,113],"critic.":[43],"The":[44,131,141],"performs":[46,159,180],"gradient":[47,61,64,115,160,169,181,231],"search":[48,116,161,182],"space":[51,165],"of":[52,68,91,110,120,127,187,193,196,198,228],"parameters":[54,135],"using":[55,114,211],"simultaneous":[56],"perturbation":[57],"stochastic":[58,129],"approximation":[59],"(SPSA)":[60],"estimates.":[62],"This":[63],"computation":[65],"requires":[66],"estimates":[67,90],"that":[71,220],"are":[72],"provided":[73],"by":[74,77],"critic":[76,96,142],"minimizing":[78],"mean":[80],"square":[81],"Bellman":[82],"error":[83],"In":[85],"order":[86],"obtain":[88,106],"good":[89],"function,":[94],"adaptively":[97],"tunes":[98],"functions":[101],"(or":[102],"features)":[104],"best":[108],"representation":[109],"Grassmanian":[119],"features.":[121,188],"Our":[122],"algorithm":[124,158,201,213,219],"makes":[125],"use":[126],"multi-timescale":[128],"approximation.":[130],"updates":[133],"its":[134],"along":[136],"slowest":[138],"time":[139,145],"scale.":[140],"uses":[143,221],"two":[144],"scales":[146],"estimate":[148],"function.":[151],"For":[152],"any":[153],"given":[154],"feature":[155],"value,":[156],"our":[157,199,212],"parameter":[164],"via":[166],"residual":[168,230],"on":[171,176],"faster":[173,235],"timescale":[174,236],"and,":[175],"medium":[178],"timescale,":[179],"Grassman":[185],"manifold":[186],"provide":[190],"an":[191],"outline":[192],"proof":[195],"convergence":[197],"locally":[204],"optimum":[205],"policy.":[206],"show":[208],"empirical":[209],"results":[210],"as":[214,216],"well":[215],"similar":[218],"temporal":[222],"difference":[223],"(TD)":[224],"learning":[225],"place":[227],"updates.":[237]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}