{"id":"https://openalex.org/W2902806543","doi":"https://doi.org/10.1145/3306309.3306321","title":"A Structure-aware Online Learning Algorithm for Markov Decision Processes","display_name":"A Structure-aware Online Learning Algorithm for Markov Decision Processes","publication_year":2019,"publication_date":"2019-02-25","ids":{"openalex":"https://openalex.org/W2902806543","doi":"https://doi.org/10.1145/3306309.3306321","mag":"2902806543"},"language":"en","primary_location":{"id":"doi:10.1145/3306309.3306321","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3306309.3306321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th EAI International Conference on Performance Evaluation Methodologies and Tools","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/A5018946124","display_name":"Arghyadip Roy","orcid":"https://orcid.org/0000-0001-9955-9514"},"institutions":[{"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":true,"raw_author_name":"Arghyadip Roy","raw_affiliation_strings":["Dept. of Electrical Engineering, IIT Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, IIT Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018541798","display_name":"Vivek S. Borkar","orcid":"https://orcid.org/0000-0003-0756-5402"},"institutions":[{"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 Borkar","raw_affiliation_strings":["Dept. of Electrical Engineering, IIT Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, IIT Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018587336","display_name":"Abhay Karandikar","orcid":"https://orcid.org/0000-0003-1608-3413"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]},{"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":"Abhay Karandikar","raw_affiliation_strings":["Dept. of Electrical Engineering, IIT Bombay, IIT Kanpur Kanpur, India"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, IIT Bombay, IIT Kanpur Kanpur, India","institution_ids":["https://openalex.org/I94234084","https://openalex.org/I162827531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034853149","display_name":"Prasanna Chaporkar","orcid":"https://orcid.org/0000-0001-5082-0179"},"institutions":[{"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":"Prasanna Chaporkar","raw_affiliation_strings":["Dept. of Electrical Engineering, IIT Bombay, Mumbai, India"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical Engineering, IIT Bombay, Mumbai, India","institution_ids":["https://openalex.org/I162827531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5018946124"],"corresponding_institution_ids":["https://openalex.org/I162827531"],"apc_list":null,"apc_paid":null,"fwci":0.5786,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.74410002,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"78"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9997000098228455,"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":0.9997000098228455,"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/T10603","display_name":"Smart Grid Energy Management","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.9980000257492065,"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":0.9078751802444458},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8264143466949463},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.77099609375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7392597198486328},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6487084627151489},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"Dynamic programming","score":0.6187716722488403},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.5838388204574585},{"id":"https://openalex.org/keywords/markov-process","display_name":"Markov process","score":0.4861904978752136},{"id":"https://openalex.org/keywords/markov-chain","display_name":"Markov chain","score":0.4155866205692291},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4081111252307892},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2691349387168884},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.23482739925384521},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16501230001449585}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.9078751802444458},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8264143466949463},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.77099609375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7392597198486328},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6487084627151489},{"id":"https://openalex.org/C37404715","wikidata":"https://www.wikidata.org/wiki/Q380679","display_name":"Dynamic programming","level":2,"score":0.6187716722488403},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5838388204574585},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.4861904978752136},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.4155866205692291},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4081111252307892},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2691349387168884},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.23482739925384521},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16501230001449585},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3306309.3306321","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3306309.3306321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th EAI International Conference on Performance Evaluation Methodologies and Tools","raw_type":"proceedings-article"},{"id":"pmh:oai:dsapce.library.iitb.ac.in:100/28063","is_oa":false,"landing_page_url":"http://dspace.library.iitb.ac.in/xmlui/handle/100/28063","pdf_url":null,"source":{"id":"https://openalex.org/S4306400899","display_name":"DSpace (IIT Bombay)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I162827531","host_organization_name":"Indian Institute of Technology Bombay","host_organization_lineage":["https://openalex.org/I162827531"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8700000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321071","display_name":"Department of Electronics and Information Technology, Ministry of Communications and Information Technology","ror":"https://ror.org/02z31cn83"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W100327610","https://openalex.org/W594357522","https://openalex.org/W1500945877","https://openalex.org/W1515851193","https://openalex.org/W1601081659","https://openalex.org/W1980922866","https://openalex.org/W2021441076","https://openalex.org/W2024780670","https://openalex.org/W2070570138","https://openalex.org/W2071983464","https://openalex.org/W2082261506","https://openalex.org/W2102195169","https://openalex.org/W2119567691","https://openalex.org/W2120465407","https://openalex.org/W2121863487","https://openalex.org/W2124715093","https://openalex.org/W2138410336","https://openalex.org/W2138717292","https://openalex.org/W2154204727","https://openalex.org/W2155027007","https://openalex.org/W2167641136","https://openalex.org/W2312609093","https://openalex.org/W2487144912","https://openalex.org/W2791825310","https://openalex.org/W2964273152"],"related_works":["https://openalex.org/W4400868993","https://openalex.org/W3096874164","https://openalex.org/W1985560493","https://openalex.org/W2937181779","https://openalex.org/W2386410636","https://openalex.org/W2357975469","https://openalex.org/W2145363145","https://openalex.org/W1626977535","https://openalex.org/W2341346307","https://openalex.org/W3168977894"],"abstract_inverted_index":{"To":[0],"overcome":[1],"the":[2,42,45,57,73,78,85,92,97,142,148],"curse":[3,7],"of":[4,8,44,60,77,127,138,147],"dimensionality":[5],"and":[6,40,108,110,136],"modeling":[9],"in":[10,105,144],"Dynamic":[11],"Programming":[12],"(DP)":[13],"methods":[14],"for":[15],"solving":[16],"classical":[17],"Markov":[18],"Decision":[19],"Process":[20],"(MDP)":[21],"problems,":[22],"Reinforcement":[23],"Learning":[24],"(RL)":[25],"algorithms":[26,154],"are":[27],"popular.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32],"consider":[33],"an":[34],"infinite-horizon":[35],"average":[36],"reward":[37],"MDP":[38],"problem":[39],"prove":[41],"optimality":[43],"threshold":[46,58,75],"policy":[47,62,80,87],"under":[48],"certain":[49],"conditions.":[50],"Traditional":[51],"RL":[52,69,115,153],"techniques":[53],"do":[54],"not":[55],"exploit":[56],"nature":[59],"optimal":[61,79,98],"while":[63,81],"learning.":[64],"We":[65,89,140],"propose":[66],"a":[67,102,124],"new":[68],"algorithm":[70,94,150],"which":[71],"utilizes":[72],"known":[74],"structure":[76],"learning":[82],"by":[83],"reducing":[84],"feasible":[86],"space.":[88],"establish":[90],"that":[91,130],"proposed":[93,118,149],"converges":[95],"to":[96,123],"policy.":[99],"It":[100],"provides":[101],"significant":[103],"improvement":[104,143],"convergence":[106,145],"speed":[107,146],"computational":[109],"storage":[111],"complexity":[112],"over":[113,151],"traditional":[114],"algorithms.":[116],"The":[117],"technique":[119],"can":[120],"be":[121],"applied":[122],"wide":[125],"variety":[126],"optimization":[128],"problems":[129],"include":[131],"energy":[132],"efficient":[133],"data":[134],"transmission":[135],"management":[137],"queues.":[139],"exhibit":[141],"other":[152],"through":[155],"simulations.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}