{"id":"https://openalex.org/W2903299703","doi":null,"title":"Approximate Dynamic Programming and Reinforcement Learning - Algorithms, Analysis and an Application","display_name":"Approximate Dynamic Programming and Reinforcement Learning - Algorithms, Analysis and an Application","publication_year":2018,"publication_date":"2018-08-13","ids":{"openalex":"https://openalex.org/W2903299703","mag":"2903299703"},"language":"en","primary_location":{"id":"mag:2903299703","doi":null,"is_oa":false,"landing_page_url":"https://etd.iisc.ac.in/handle/2005/3963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"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/A5044247596","display_name":"Chandrashekar Lakshminarayanan","orcid":"https://orcid.org/0000-0002-3570-7175","observed_orcids":["https://orcid.org/0000-0002-3570-7175"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chandrashekar Lakshminarayanan","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3570-7175","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5044247596"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5526999831199646,"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":0.5526999831199646,"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":0.4368000030517578,"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"}},{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.0010000000474974513,"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/approximate-dynamic-programming","display_name":"approximate dynamic programming","score":0.996999979019165},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9750000238418579},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.5820000171661377},{"id":"https://openalex.org/keywords/approximate-value-iteration","display_name":"approximate value iteration","score":0.5410000085830688},{"id":"https://openalex.org/keywords/approximate-policy-iteration","display_name":"approximate policy iteration","score":0.675000011920929},{"id":"https://openalex.org/keywords/linear-programming","display_name":"linear programming","score":0.47699999809265137},{"id":"https://openalex.org/keywords/linear-function-approximation","display_name":"linear function approximation","score":0.7450000047683716},{"id":"https://openalex.org/keywords/performance-bounds","display_name":"performance bounds","score":0.4480000138282776},{"id":"https://openalex.org/keywords/crowdsourcing","display_name":"crowdsourcing","score":0.4449999928474426}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.8737249970436096},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.8368420600891113},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7955818176269531},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6995701789855957},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6123279929161072},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.5797510743141174},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5407500267028809},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5118400454521179},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.5002877712249756},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.4823031425476074},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.4785107672214508},{"id":"https://openalex.org/C170131372","wikidata":"https://www.wikidata.org/wiki/Q7617811","display_name":"Stochastic control","level":3,"score":0.42435258626937866},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.41677647829055786},{"id":"https://openalex.org/C137631369","wikidata":"https://www.wikidata.org/wiki/Q7617831","display_name":"Stochastic programming","level":2,"score":0.4116200804710388},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3336266279220581},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3236779570579529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1567145586013794},{"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2903299703","doi":null,"is_oa":false,"landing_page_url":"https://etd.iisc.ac.in/handle/2005/3963","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2963185456","https://openalex.org/W2159858017","https://openalex.org/W3119125477","https://openalex.org/W4372056483","https://openalex.org/W1944780172","https://openalex.org/W6940190767","https://openalex.org/W2128090816","https://openalex.org/W2143031849","https://openalex.org/W2120406836","https://openalex.org/W1601081659"],"abstract_inverted_index":{"Problems":[0],"involving":[1],"optimal":[2,38,43,83,88,242],"sequential":[3],"making":[4],"in":[5,10,24,97,107,122,131,170,208,219,228,262,378,412],"uncertain":[6],"dynamic":[7,48],"systems":[8,261],"arise":[9],"domains":[11],"such":[12,260],"as":[13,452],"engineering,":[14],"science":[15],"and":[16,41,51,74,86,106,137,159,162,253,295,331,355,377],"economics.":[17],"Such":[18],"problems":[19,244],"can":[20],"often":[21,104],"be":[22],"cast":[23],"the":[25,37,42,52,58,82,87,91,100,125,132,171,182,214,217,220,226,229,290,302,325,337,340,361,369,398,402,405,432,457,461,468],"framework":[26,471],"of":[27,47,60,134,168,173,184,216,311,314,339,350,371,375,394,401,447,456,460],"Markov":[28],"Decision":[29],"Process":[30],"(MDP).":[31],"Solving":[32],"an":[33,165,190],"MDP":[34],"requires":[35],"computing":[36,189],"value":[39,70,84,192],"function":[40,85,193,352],"policy.":[44,89,197,342],"The":[45,63,77,388,463],"idea":[46],"programming":[49],"(DP)":[50],"Bellman":[53],"equation":[54],"(BE)":[55],"are":[56,69,95,128,202,248,276,329,416,450],"at":[57],"heart":[59],"solution":[61,304],"methods.":[62],"three":[64],"important":[65],"exact":[66,78,92],"DP":[67,79,93],"methods":[68,80,94,116,180,255,328],"iteration,":[71],"policy":[72],"iteration":[73],"linear":[75,222,232,252,309,351,382,439,454],"programming.":[76],"compute":[81,118],"However,":[90,264],"inadequate":[96],"practice":[98],"because":[99],"state":[101,186],"space":[102,187],"is":[103,235,266,305,363,385,407,467],"large":[105,185,373],"practice,":[108,379],"one":[109],"might":[110],"have":[111,256],"to":[112,114,140,157,268,365,368,409,434,473],"resort":[113],"approximate":[115,158,191,303],"that":[117,143,206,240,270,324,449],"sub-optimal":[119,196,341],"policies.":[120,211],"Further,":[121],"certain":[123],"cases,":[124],"system":[126],"observations":[127],"known":[129,238,408],"only":[130,418],"form":[133],"noisy":[135],"samples":[136],"we":[138,151,201,224,332,430],"need":[139],"design":[141],"algorithms":[142],"learn":[144],"from":[145,397],"these":[146],"samples.":[147],"In":[148,198,427],"this":[149,199,428],"thesis":[150],"study":[152,225],"interesting":[153,166],"theoretical":[154,357,414,470],"questions":[155],"pertaining":[156],"learning":[160],"algorithms,":[161],"also":[163],"present":[164,333],"application":[167],"MDPs":[169,275],"domain":[172],"crowd":[174],"sourcing.":[175],"\nApproximate":[176],"Dynamic":[177],"Programming":[178],"(ADP)":[179],"handle":[181],"issue":[183],"by":[188,213],"and/or":[194],"a":[195,236,306,312,320,334,372,380,391,420,436,444],"thesis,":[200,429],"concerned":[203],"with":[204,245],"conditions":[205],"result":[207],"provably":[209],"good":[210],"Motivated":[212],"limitations":[215],"PBE":[218,227],"conventional":[221],"algebra,":[223],"(min,":[230,249,278,307],"+)":[231,251,279,282,308],"algebra.":[233],"It":[234],"well":[237,411],"fact":[239],"deterministic":[241],"control":[243],"cost/reward":[246],"criterion":[247],"+)/(max,":[250],"ADP":[254,287,327],"been":[257],"developed":[258,472],"for":[259,419,477],"literature.":[263],"it":[265],"straightforward":[267],"show":[269,323],"in\ufb01nite":[271],"horizon":[272],"discounted":[273],"reward/cost":[274],"neither":[277],"nor":[280],"(max,":[281],"linear.":[283],"We":[284,322],"develop":[285],"novel":[286,469],"schemes":[288],"namely":[289],"Approximate":[291,297,344],"Q":[292,298],"Iteration":[293,299],"(AQI)":[294],"Variational":[296],"(VAQI),":[300],"where":[301],"combination":[310],"set":[313],"basis":[315],"functions":[316],"whose":[317],"span":[318],"constitutes":[319],"subsemimodule.":[321],"new":[326],"convergent":[330],"bound":[335],"on":[336],"performance":[338,358],"\nThe":[343],"Linear":[345],"Program":[346],"(ALP)":[347],"makes":[348],"use":[349],"approximation":[353],"(LFA)":[354],"o\ufb00ers":[356],"guarantees.":[359],"Nevertheless,":[360],"ALP":[362],"di\ufb03cult":[364],"solve":[366],"due":[367],"presence":[370],"number":[374,393,446],"constraints":[376,395,400,448,459],"reduced":[381,438],"program":[383,440],"(RLP)":[384],"solved":[386],"instead.":[387],"RLP":[389,406,422,433],"has":[390,443],"tractable":[392,445],"sampled":[396],"original":[399,458],"ALP.":[403,462],"Though":[404],"perform":[410],"experiments,":[413],"guarantees":[415],"available":[417],"speci\ufb01c":[421],"obtained":[423,451],"under":[424],"idealized":[425],"assumptions.":[426],"generalize":[431],"de\ufb01ne":[435],"generalized":[437],"(GRLP)":[441],"which":[442],"positive":[453],"combinations":[455],"main":[464],"contribution":[465],"here":[466],"obtain":[474],"error":[475],"bounds":[476],"any\u2026":[478]},"counts_by_year":[],"updated_date":"2025-11-06T04:12:42.849631","created_date":"2018-12-11T00:00:00"}