{"id":"https://openalex.org/W2132322158","doi":"https://doi.org/10.1109/acc.2007.4282587","title":"Parametrized Actor-Critic Algorithms for Finite-Horizon MDPs","display_name":"Parametrized Actor-Critic Algorithms for Finite-Horizon MDPs","publication_year":2007,"publication_date":"2007-07-01","ids":{"openalex":"https://openalex.org/W2132322158","doi":"https://doi.org/10.1109/acc.2007.4282587","mag":"2132322158"},"language":"en","primary_location":{"id":"doi:10.1109/acc.2007.4282587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2007.4282587","pdf_url":null,"source":{"id":"https://openalex.org/S4210168941","display_name":"Proceedings of the ... American Control Conference/Proceedings of the American Control Conference","issn_l":"0743-1619","issn":["0743-1619","2378-5861"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 American Control Conference","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/A5057952216","display_name":"Mohammed Shahid Abdulla","orcid":"https://orcid.org/0000-0002-0464-0617"},"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":"Mohammed Shahid Abdulla","raw_affiliation_strings":["Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India","Indian Institute of Science Bangalore"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Indian Institute of Science Bangalore","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","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, Bangalore, India","Indian Institute of Science Bangalore"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]},{"raw_affiliation_string":"Indian Institute of Science Bangalore","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5057952216"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.23913787,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"534","last_page":"539"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9991000294685364,"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":0.9991000294685364,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.9968000054359436,"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/T12056","display_name":"Markov Chains and Monte Carlo Methods","score":0.9904999732971191,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recursion","display_name":"Recursion (computer science)","score":0.8757888674736023},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.7813853621482849},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.7108970880508423},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.680989682674408},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5878770351409912},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5774011015892029},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.5631489753723145},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.5321131348609924},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4274548292160034},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.42344963550567627},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.40010666847229004},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3933265507221222},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23345249891281128},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1732107400894165},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.13360345363616943},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.10539451241493225}],"concepts":[{"id":"https://openalex.org/C168773036","wikidata":"https://www.wikidata.org/wiki/Q264164","display_name":"Recursion (computer science)","level":2,"score":0.8757888674736023},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7813853621482849},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.7108970880508423},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.680989682674408},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5878770351409912},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5774011015892029},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.5631489753723145},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5321131348609924},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4274548292160034},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.42344963550567627},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.40010666847229004},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3933265507221222},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23345249891281128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1732107400894165},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.13360345363616943},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.10539451241493225},{"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/acc.2007.4282587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acc.2007.4282587","pdf_url":null,"source":{"id":"https://openalex.org/S4210168941","display_name":"Proceedings of the ... American Control Conference/Proceedings of the American Control Conference","issn_l":"0743-1619","issn":["0743-1619","2378-5861"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2007 American Control Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.iisc.ac.in:26811","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4377196309","display_name":"NOT FOUND REPOSITORY (Indian Institute of Science Bangalore)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.142.2448","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.142.2448","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jhuapl.edu/SPSA/PDF-SPSA/Abdulla_Bhatnagar_ACC07.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320719","display_name":"Department of Science and Technology, Ministry of Science and Technology, India","ror":"https://ror.org/0101xrq71"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1597303641","https://openalex.org/W2009303086","https://openalex.org/W2061769118","https://openalex.org/W2107384771","https://openalex.org/W2120465407","https://openalex.org/W2124289529","https://openalex.org/W2139418546","https://openalex.org/W2156168464","https://openalex.org/W2156737235","https://openalex.org/W2160522427","https://openalex.org/W2173945562","https://openalex.org/W2235056388","https://openalex.org/W2322524800","https://openalex.org/W2595250839","https://openalex.org/W6635767209","https://openalex.org/W6666110301","https://openalex.org/W6734616217"],"related_works":["https://openalex.org/W1976679120","https://openalex.org/W4296209631","https://openalex.org/W4281614748","https://openalex.org/W2377519369","https://openalex.org/W2997055691","https://openalex.org/W1975732908","https://openalex.org/W187740018","https://openalex.org/W2162286586","https://openalex.org/W4255368532","https://openalex.org/W2132322158"],"abstract_inverted_index":{"Due":[0],"to":[1,34,79,93,144,157],"their":[2],"non-stationarity,":[3],"finite-horizon":[4],"Markov":[5],"decision":[6],"processes":[7,129],"(FH-MDPs)":[8],"have":[9],"one":[10],"probability":[11],"transition":[12],"matrix":[13],"per":[14],"stage.":[15],"Thus":[16],"the":[17,43,54,66,85,97,145,158],"curse":[18],"of":[19,126,161],"dimensionality":[20],"affects":[21],"FH-MDPs":[22,108],"more":[23],"severely":[24],"than":[25],"infinite-horizon":[26],"MDPs.":[27],"We":[28,88,132],"propose":[29],"two":[30],"parametrized":[31,55],"'actor-critic'":[32],"algorithms":[33,41],"compute":[35],"optimal":[36],"policies":[37],"for":[38,100,107,123],"FH-MDPs.":[39],"Both":[40],"use":[42],"two-timescale":[44],"stochastic":[45,124],"approximation":[46],"technique,":[47],"thus":[48],"simultaneously":[49],"performing":[50],"gradient":[51,68],"search":[52],"in":[53,77,153],"policy":[56,67,136],"space":[57],"(the":[58,69],"'actor')":[59],"on":[60],"a":[61,72,94,120],"slower":[62],"timescale":[63],"and":[64],"learning":[65],"'critic')":[70],"via":[71],"faster":[73],"recursion.":[74,148],"This":[75],"is":[76,106,130],"contrast":[78],"methods":[80,138],"where":[81],"critic":[82,143],"recursions":[83],"learn":[84],"cost-to-go":[86],"proper.":[87],"show":[89],"w.p":[90],"1":[91],"convergence":[92],"set":[95],"with":[96,109],"necessary":[98],"condition":[99],"constrained":[101],"optima.":[102],"The":[103],"proposed":[104,146],"parameterization":[105],"compact":[110],"action":[111],"sets,":[112],"although":[113],"certain":[114],"exceptions":[115],"can":[116],"be":[117],"handled.":[118],"Further,":[119],"third":[121],"algorithm":[122],"control":[125],"stopping":[127],"time":[128],"presented.":[131],"explain":[133],"why":[134],"current":[135],"evaluation":[137],"do":[139],"not":[140],"work":[141],"as":[142],"actor":[147],"Simulation":[149],"results":[150],"from":[151],"flow-control":[152],"communication":[154],"networks":[155],"attest":[156],"performance":[159],"advantages":[160],"all":[162],"three":[163],"algorithms.":[164]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}