{"id":"https://openalex.org/W3199561448","doi":"https://doi.org/10.1109/tac.2021.3112851","title":"Generalized Second-Order Value Iteration in Markov Decision Processes","display_name":"Generalized Second-Order Value Iteration in Markov Decision Processes","publication_year":2021,"publication_date":"2021-09-16","ids":{"openalex":"https://openalex.org/W3199561448","doi":"https://doi.org/10.1109/tac.2021.3112851","mag":"3199561448"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2021.3112851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3112851","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1905.03927","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059738367","display_name":"Chandramouli Kamanchi","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":"Chandramouli Kamanchi","raw_affiliation_strings":["Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002033038","display_name":"Raghuram Bharadwaj Diddigi","orcid":"https://orcid.org/0000-0003-0233-0698"},"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":"Raghuram Bharadwaj Diddigi","raw_affiliation_strings":["Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India","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, Bengaluru, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bengaluru, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5059738367"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.5599,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.73563971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"67","issue":"8","first_page":"4241","last_page":"4247"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.995199978351593,"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":0.995199978351593,"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9934999942779541,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9923999905586243,"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/markov-decision-process","display_name":"Markov decision process","score":0.8075488805770874},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.6404204368591309},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.622306227684021},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.6213836073875427},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.5887531042098999},{"id":"https://openalex.org/keywords/relaxation","display_name":"Relaxation (psychology)","score":0.5188299417495728},{"id":"https://openalex.org/keywords/applied-mathematics","display_name":"Applied mathematics","score":0.5151573419570923},{"id":"https://openalex.org/keywords/fixed-point-iteration","display_name":"Fixed-point iteration","score":0.5073415637016296},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4852294921875},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4788758158683777},{"id":"https://openalex.org/keywords/fixed-point","display_name":"Fixed point","score":0.47674334049224854},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.46841517090797424},{"id":"https://openalex.org/keywords/power-iteration","display_name":"Power iteration","score":0.4491267204284668},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.44239723682403564},{"id":"https://openalex.org/keywords/newtons-method","display_name":"Newton's method","score":0.43495437502861023},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4224150776863098},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.42169812321662903},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.24090364575386047},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.13264667987823486},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07443952560424805}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8075488805770874},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.6404204368591309},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.622306227684021},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6213836073875427},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5887531042098999},{"id":"https://openalex.org/C2776029896","wikidata":"https://www.wikidata.org/wiki/Q3935810","display_name":"Relaxation (psychology)","level":2,"score":0.5188299417495728},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.5151573419570923},{"id":"https://openalex.org/C157449380","wikidata":"https://www.wikidata.org/wiki/Q1030759","display_name":"Fixed-point iteration","level":3,"score":0.5073415637016296},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4852294921875},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4788758158683777},{"id":"https://openalex.org/C61445026","wikidata":"https://www.wikidata.org/wiki/Q217608","display_name":"Fixed point","level":2,"score":0.47674334049224854},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.46841517090797424},{"id":"https://openalex.org/C162443888","wikidata":"https://www.wikidata.org/wiki/Q1426504","display_name":"Power iteration","level":3,"score":0.4491267204284668},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.44239723682403564},{"id":"https://openalex.org/C85189116","wikidata":"https://www.wikidata.org/wiki/Q374195","display_name":"Newton's method","level":3,"score":0.43495437502861023},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4224150776863098},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.42169812321662903},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.24090364575386047},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.13264667987823486},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07443952560424805},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tac.2021.3112851","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3112851","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1905.03927","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03927","pdf_url":"https://arxiv.org/pdf/1905.03927","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1905.03927","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1905.03927","pdf_url":"https://arxiv.org/pdf/1905.03927","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310071","display_name":"Indian Institute of Science","ror":"https://ror.org/04dese585"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W173318062","https://openalex.org/W594357522","https://openalex.org/W1557517019","https://openalex.org/W1757796397","https://openalex.org/W2042680115","https://openalex.org/W2082860493","https://openalex.org/W2090963365","https://openalex.org/W2167732364","https://openalex.org/W2565081646","https://openalex.org/W2594103415","https://openalex.org/W2751801093","https://openalex.org/W2781726626","https://openalex.org/W2806985155","https://openalex.org/W2919115771","https://openalex.org/W2946258294","https://openalex.org/W2949350092","https://openalex.org/W3105579180","https://openalex.org/W3122896188","https://openalex.org/W4237591687","https://openalex.org/W4243772471","https://openalex.org/W4297926604","https://openalex.org/W6637967152","https://openalex.org/W6730905388","https://openalex.org/W6734517396","https://openalex.org/W6743500281","https://openalex.org/W6747473740","https://openalex.org/W6752164047"],"related_works":["https://openalex.org/W3133735177","https://openalex.org/W2152670157","https://openalex.org/W4308702637","https://openalex.org/W2386410636","https://openalex.org/W4285292047","https://openalex.org/W4221146748","https://openalex.org/W4283698953","https://openalex.org/W4281381373","https://openalex.org/W4225693019","https://openalex.org/W2348977732"],"abstract_inverted_index":{"Value":[0,40],"iteration":[1,6,41,114,129],"is":[2,29,42,64,117],"a":[3,18,26,43,51,65,74,87,111],"fixed":[4,75],"point":[5,76],"technique":[7,67,95],"utilized":[8],"to":[9,34,56,58,72,124,139],"obtain":[10],"the":[11,37,59,83,91,97,121,125,133,140,146,153],"optimal":[12,38,60,98,141],"value":[13,99,104,113,128],"function":[14,100],"and":[15,31,144],"policy":[16],"in":[17,82],"discounted":[19],"reward":[20],"Markov":[21],"decision":[22],"process":[23],"(MDP).":[24],"Here,":[25],"contraction":[27],"operator":[28],"constructed":[30],"applied":[32,71],"repeatedly":[33],"arrive":[35],"at":[36],"solution.":[39,61],"first-order":[44],"method":[45,123],"and,":[46],"therefore,":[47],"it":[48],"may":[49],"take":[50],"large":[52],"number":[53],"of":[54,90,136,155],"iterations":[55],"converge":[57],"Successive":[62],"relaxation":[63,127],"popular":[66],"that":[68,85,116],"can":[69],"be":[70],"solve":[73],"equation.":[77],"It":[78],"has":[79],"been":[80],"shown":[81],"literature":[84],"under":[86],"special":[88],"structure":[89],"MDP,":[92],"successive":[93,126],"overrelaxation":[94],"computes":[96],"faster":[101],"than":[102],"standard":[103],"iteration.":[105],"In":[106],"this":[107],"article,":[108],"we":[109,151],"propose":[110],"second-order":[112,147],"procedure":[115],"obtained":[118],"by":[119],"applying":[120],"Newton\u2013Raphson":[122],"scheme.":[130],"We":[131],"prove":[132],"global":[134],"convergence":[135],"our":[137,156],"algorithm":[138],"solution":[142],"asymptotically":[143],"show":[145],"convergence.":[148],"Through":[149],"experiments,":[150],"demonstrate":[152],"effectiveness":[154],"proposed":[157],"approach.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
