{"id":"https://openalex.org/W2963185456","doi":"https://doi.org/10.1109/cdc.2014.7039626","title":"Approximate Dynamic Programming with (min; +) linear function approximation for Markov decision processes","display_name":"Approximate Dynamic Programming with (min; +) linear function approximation for Markov decision processes","publication_year":2014,"publication_date":"2014-12-01","ids":{"openalex":"https://openalex.org/W2963185456","doi":"https://doi.org/10.1109/cdc.2014.7039626","mag":"2963185456"},"language":"en","primary_location":{"id":"doi:10.1109/cdc.2014.7039626","doi":"https://doi.org/10.1109/cdc.2014.7039626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7039626","pdf_url":null,"source":{"id":"https://openalex.org/S4210221977","display_name":"IEEE Conference on Decision and Control (CDC)","issn_l":"0191-2216","issn":["0191-2216"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"53rd IEEE Conference on Decision and Control","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5083195854","display_name":"L. N. Chandrashekar","orcid":"https://orcid.org/0009-0000-3146-4164","observed_orcids":["https://orcid.org/0009-0000-3146-4164"]},"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":"L. Chandrashekar","raw_affiliation_strings":["Department of Computer Science and Automation, Indian Institute of Science, Bangalore, Karnataka, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bangalore, Karnataka, IN","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","observed_orcids":["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, Karnataka, IN"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Automation, Indian Institute of Science, Bangalore, Karnataka, IN","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.4048,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.42554764,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1588","last_page":"1593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9380000233650208,"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"}},"topics":[{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9380000233650208,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.05040000006556511,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.003599999938160181,"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":0.9990000128746033},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.8949999809265137},{"id":"https://openalex.org/keywords/min-algebra","display_name":"(min,+) algebra","score":0.8799999952316284},{"id":"https://openalex.org/keywords/tropical-semiring","display_name":"tropical semiring","score":0.7540000081062317},{"id":"https://openalex.org/keywords/linear-function-approximation","display_name":"linear function approximation","score":0.953000009059906},{"id":"https://openalex.org/keywords/optimal-policy","display_name":"optimal policy","score":0.546999990940094},{"id":"https://openalex.org/keywords/value-function-approximation","display_name":"value function approximation","score":0.8450000286102295},{"id":"https://openalex.org/keywords/convergence-analysis","display_name":"convergence analysis","score":0.7099999785423279},{"id":"https://openalex.org/keywords/sequential-decision-making-under-uncertainty","display_name":"sequential decision making under uncertainty","score":0.6909999847412109}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.7812662720680237},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.7558404803276062},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6134803295135498},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6028721928596497},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.5466320514678955},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.5028292536735535},{"id":"https://openalex.org/C57493831","wikidata":"https://www.wikidata.org/wiki/Q3134666","display_name":"Projection (relational algebra)","level":2,"score":0.4783327579498291},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.4727947413921356},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.459780752658844},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.45969098806381226},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.43358489871025085},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.43326032161712646},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.4198182225227356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3975900411605835},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.368587464094162},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24932977557182312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.08708623051643372},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"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/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc.2014.7039626","doi":"https://doi.org/10.1109/cdc.2014.7039626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc.2014.7039626","pdf_url":null,"source":{"id":"https://openalex.org/S4210221977","display_name":"IEEE Conference on Decision and Control (CDC)","issn_l":"0191-2216","issn":["0191-2216"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"53rd IEEE Conference on Decision and Control","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1745373831","https://openalex.org/W1969670175","https://openalex.org/W1970266193","https://openalex.org/W2094860060","https://openalex.org/W2098432798","https://openalex.org/W2119567691","https://openalex.org/W2164674108","https://openalex.org/W2334782222"],"related_works":["https://openalex.org/W1944780172","https://openalex.org/W7095324241","https://openalex.org/W2903299703","https://openalex.org/W4372056483","https://openalex.org/W7098501758","https://openalex.org/W2284587995","https://openalex.org/W2120406836","https://openalex.org/W7101163364","https://openalex.org/W2159858017","https://openalex.org/W2143031849"],"abstract_inverted_index":{"Markov":[0],"Decision":[1],"Process":[2],"(MDP)":[3],"is":[4,24,41,55,73,132,177,195,205],"a":[5,120,124,135,178,184,192,198],"useful":[6],"framework":[7],"to":[8,25,75],"study":[9],"problems":[10],"of":[11,80,89,104,126,140,183,186,234,243],"optimal":[12,28,34,38,46,61],"sequential":[13],"decision":[14],"making":[15],"under":[16],"uncertainty.":[17],"Given":[18],"any":[19],"MDP":[20],"the":[21,27,33,37,45,50,60,68,77,115,145,169,174,202,231,235,241,259],"aim":[22],"here":[23],"find":[26],"action":[29],"selection":[30],"mechanism":[31],"i.e.,":[32,114],"policy.":[35],"Typically,":[36],"policy":[39],"(u*)":[40],"obtained":[42,57,133,196],"by":[43,58,99,123],"substituting":[44],"value-function":[47],"(J*)":[48],"in":[49,119,151,168,213,252],"Bellman":[51],"equation.":[52],"Alternatively,":[53],"u*":[54],"also":[56,248],"learning":[59],"state-action":[62],"value":[63],"function":[64,111],"Q*":[65,83],"known":[66],"as":[67],"Q":[69],"value-function.":[70],"However,":[71],"it":[72],"difficult":[74],"compute":[76],"exact":[78],"values":[79],"J*":[81],"or":[82],"for":[84,163,255],"MDPs":[85,164,220,256],"with":[86],"large":[87],"number":[88],"states.":[90],"Approximate":[91],"Dynamic":[92],"Programming":[93],"(ADP)":[94],"methods":[95,108,162,215,254],"address":[96],"this":[97,157],"difficulty":[98],"computing":[100],"lower":[101],"dimensional":[102,142],"approximations":[103],"J*/Q*.":[105],"Most":[106],"ADP":[107,161,214,245,253],"employ":[109],"linear":[110,136,181,208,225],"approximation":[112,131],"(LFA),":[113],"approximate":[116,175],"solution":[117,176],"lies":[118],"subspace":[121],"spanned":[122],"family":[125],"pre-selected":[127],"basis":[128,187],"functions.":[129],"The":[130],"via":[134,197],"least":[137,209],"squares":[138,210],"projection":[139,199,211,236],"higher":[141],"quantities":[143],"and":[144,153],"L2norm":[146],"plays":[147],"an":[148],"important":[149],"role":[150],"convergence":[152,242],"error":[154],"analysis.":[155],"In":[156],"paper,":[158],"we":[159,228],"discuss":[160,249],"based":[165,216,257],"on":[166,217,258],"LFAs":[167],"(min,":[170,179,223,260],"+)":[171,180,224,261],"algebra.":[172],"Here":[173],"combination":[182],"set":[185],"functions":[188],"whose":[189],"span":[190],"constitutes":[191],"subsemimodule.":[193],"Approximation":[194],"operator":[200,237],"onto":[201],"subsemimodule":[203],"which":[204],"different":[206],"from":[207],"used":[212],"conventional":[218],"LFAs.":[219,262],"are":[221],"not":[222],"systems,":[226],"nevertheless,":[227],"show":[229],"that":[230],"monotonicity":[232],"property":[233],"helps":[238],"us":[239],"establish":[240],"our":[244],"schemes.":[246],"We":[247],"future":[250],"directions":[251]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2017,"cited_by_count":1}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2019-07-30T00:00:00"}