{"id":"https://openalex.org/W2803402623","doi":"https://doi.org/10.1109/ciss.2018.8362275","title":"Exploiting policy structure for solving MDPs with large state space","display_name":"Exploiting policy structure for solving MDPs with large state space","publication_year":2018,"publication_date":"2018-03-01","ids":{"openalex":"https://openalex.org/W2803402623","doi":"https://doi.org/10.1109/ciss.2018.8362275","mag":"2803402623"},"language":"en","primary_location":{"id":"doi:10.1109/ciss.2018.8362275","doi":"https://doi.org/10.1109/ciss.2018.8362275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss.2018.8362275","pdf_url":null,"source":{"id":"https://openalex.org/S4306418066","display_name":"Conference on Information Sciences and Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 52nd Annual Conference on Information Sciences and Systems (CISS)","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/A5023414890","display_name":"Libin Liu","orcid":"https://orcid.org/0000-0003-0123-942X","observed_orcids":["https://orcid.org/0000-0003-0123-942X"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Libin Liu","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, US","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086971942","display_name":"Arpan Chattopadhyay","orcid":"https://orcid.org/0000-0002-2684-5912","observed_orcids":["https://orcid.org/0000-0002-2684-5912"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Arpan Chattopadhyay","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, US","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072739163","display_name":"Urbashi Mitra","orcid":"https://orcid.org/0000-0002-8896-1177","observed_orcids":["https://orcid.org/0000-0002-8896-1177"]},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Urbashi Mitra","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, US","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":1.0465,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.70703252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9336000084877014,"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":0.9336000084877014,"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/T11409","display_name":"Advanced Wireless Network Optimization","score":0.020500000566244125,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.019999999552965164,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.9980000257492065},{"id":"https://openalex.org/keywords/large-state-spaces","display_name":"large state spaces","score":0.8320000171661377},{"id":"https://openalex.org/keywords/optimal-control-policy","display_name":"optimal control policy","score":0.8399999737739563},{"id":"https://openalex.org/keywords/wireless-networks","display_name":"wireless networks","score":0.8669999837875366},{"id":"https://openalex.org/keywords/policy-structure","display_name":"policy structure","score":0.8029999732971191},{"id":"https://openalex.org/keywords/subspace-approximation","display_name":"subspace approximation","score":0.8140000104904175},{"id":"https://openalex.org/keywords/reduced-dimensionality","display_name":"reduced dimensionality","score":0.5180000066757202},{"id":"https://openalex.org/keywords/convergence-rate","display_name":"convergence rate","score":0.75},{"id":"https://openalex.org/keywords/value-iteration","display_name":"value iteration","score":0.7860000133514404},{"id":"https://openalex.org/keywords/policy-iteration","display_name":"policy iteration","score":0.9990000128746033}],"concepts":[{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.844274640083313},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.713369607925415},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.6910194158554077},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6814022064208984},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.6680952906608582},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.6365214586257935},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6298675537109375},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.5496198534965515},{"id":"https://openalex.org/C108037233","wikidata":"https://www.wikidata.org/wiki/Q11375","display_name":"Wireless network","level":3,"score":0.5369998812675476},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.510452389717102},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4764043390750885},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.45923930406570435},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.42139044404029846},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.42082738876342773},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41062265634536743},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2027483880519867},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20266610383987427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13774019479751587},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.11299830675125122},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0972311794757843},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ciss.2018.8362275","doi":"https://doi.org/10.1109/ciss.2018.8362275","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ciss.2018.8362275","pdf_url":null,"source":{"id":"https://openalex.org/S4306418066","display_name":"Conference on Information Sciences and Systems","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 52nd Annual Conference on Information Sciences and Systems (CISS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W223326216","https://openalex.org/W247697463","https://openalex.org/W1745373831","https://openalex.org/W1971585841","https://openalex.org/W2004559848","https://openalex.org/W2058735307","https://openalex.org/W2101491865","https://openalex.org/W2150844583","https://openalex.org/W2157613936","https://openalex.org/W2158787690","https://openalex.org/W2171092272","https://openalex.org/W2336230354","https://openalex.org/W2531149756","https://openalex.org/W2586428935","https://openalex.org/W2782709542"],"related_works":["https://openalex.org/W2912285628","https://openalex.org/W2782709542","https://openalex.org/W6964378238","https://openalex.org/W4360584597","https://openalex.org/W2053235372","https://openalex.org/W2084873914","https://openalex.org/W4312814819","https://openalex.org/W2336230354","https://openalex.org/W2056393182","https://openalex.org/W2909648661"],"abstract_inverted_index":{"Markov":[0],"decision":[1],"processes":[2],"provide":[3],"good":[4],"models":[5],"for":[6,22,53],"many":[7],"systems,":[8],"including":[9],"wireless":[10,23],"communication":[11],"networks.":[12,24,57],"The":[13,93],"goal":[14],"herein":[15],"is":[16,75],"to":[17,38,64,86],"develop":[18],"optimal":[19,40,66],"control":[20],"policies":[21,41],"While":[25],"classical":[26],"methods":[27],"such":[28],"as":[29],"value":[30],"iteration":[31,34],"and":[32],"policy":[33,82],"have":[35],"been":[36,62],"employed":[37,63],"determine":[39,87],"in":[42,68,89],"a":[43,90,102,107],"moderate":[44],"complexity":[45,51],"manner;":[46],"they":[47],"still":[48],"suffer":[49],"from":[50],"challenges":[52],"very":[54],"large":[55],"scale":[56],"Previously,":[58],"subspace":[59],"approximation":[60],"has":[61],"find":[65],"controllers":[67],"reduced":[69,91],"dimensions.":[70],"Herein,":[71],"an":[72],"alternative":[73],"approach":[74,100],"considered":[76],"wherein":[77],"the":[78,81],"properties":[79],"of":[80,110],"structure":[83],"are":[84],"exploited":[85],"solutions":[88],"dimension.":[92],"numerical":[94],"results":[95],"show":[96],"that":[97],"this":[98],"new":[99],"achieves":[101],"faster":[103],"convergence":[104],"rate":[105],"with":[106],"negligible":[108],"loss":[109],"performance.":[111]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2018-06-01T00:00:00"}