{"id":"https://openalex.org/W4382936058","doi":"https://doi.org/10.23919/acc55779.2023.10155973","title":"On the Benefits of Leveraging Structural Information in Planning Over the Learned Model","display_name":"On the Benefits of Leveraging Structural Information in Planning Over the Learned Model","publication_year":2023,"publication_date":"2023-05-31","ids":{"openalex":"https://openalex.org/W4382936058","doi":"https://doi.org/10.23919/acc55779.2023.10155973"},"language":"en","primary_location":{"id":"doi:10.23919/acc55779.2023.10155973","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc55779.2023.10155973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 American Control Conference (ACC)","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/A5033886406","display_name":"Jiajun Shen","orcid":"https://orcid.org/0000-0002-5042-0201"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jiajun Shen","raw_affiliation_strings":["Purdue University,Elmore Family School of Electrical Computer Engineering,West Lafayette,IL,USA,47906"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Elmore Family School of Electrical Computer Engineering,West Lafayette,IL,USA,47906","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019598276","display_name":"Kananart Kuwaranancharoen","orcid":"https://orcid.org/0000-0002-0769-1399"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kananart Kuwaranancharoen","raw_affiliation_strings":["Purdue University,Elmore Family School of Electrical Computer Engineering,West Lafayette,IL,USA,47906"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Elmore Family School of Electrical Computer Engineering,West Lafayette,IL,USA,47906","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078114699","display_name":"Raid Ayoub","orcid":"https://orcid.org/0000-0002-1175-2983"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Raid Ayoub","raw_affiliation_strings":["Intel Corporation,Hillsboro,OR,USA,97124"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation,Hillsboro,OR,USA,97124","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020615383","display_name":"Pietro Mercati","orcid":"https://orcid.org/0000-0003-2842-7201"},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pietro Mercati","raw_affiliation_strings":["Intel Corporation,Hillsboro,OR,USA,97124"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Corporation,Hillsboro,OR,USA,97124","institution_ids":["https://openalex.org/I1343180700"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076731201","display_name":"Shreyas Sundaram","orcid":"https://orcid.org/0000-0002-5390-2505"},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shreyas Sundaram","raw_affiliation_strings":["Purdue University,Elmore Family School of Electrical Computer Engineering,West Lafayette,IL,USA,47906"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University,Elmore Family School of Electrical Computer Engineering,West Lafayette,IL,USA,47906","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53883501,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4555","last_page":"4560"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9959999918937683,"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":0.9959999918937683,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9914000034332275,"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/T11195","display_name":"Simulation Techniques and Applications","score":0.989300012588501,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7864324450492859},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.761490523815155},{"id":"https://openalex.org/keywords/sample-complexity","display_name":"Sample complexity","score":0.6930704116821289},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.6344550848007202},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5921088457107544},{"id":"https://openalex.org/keywords/bellman-equation","display_name":"Bellman equation","score":0.5257426500320435},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5199024081230164},{"id":"https://openalex.org/keywords/server","display_name":"Server","score":0.4488803744316101},{"id":"https://openalex.org/keywords/value-of-information","display_name":"Value of information","score":0.44614970684051514},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.3398096561431885},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33351677656173706},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3332410454750061},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13927054405212402}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7864324450492859},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.761490523815155},{"id":"https://openalex.org/C2778445095","wikidata":"https://www.wikidata.org/wiki/Q18354077","display_name":"Sample complexity","level":2,"score":0.6930704116821289},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.6344550848007202},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5921088457107544},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.5257426500320435},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5199024081230164},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.4488803744316101},{"id":"https://openalex.org/C92424840","wikidata":"https://www.wikidata.org/wiki/Q7912772","display_name":"Value of information","level":2,"score":0.44614970684051514},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3398096561431885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33351677656173706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3332410454750061},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13927054405212402},{"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/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"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/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc55779.2023.10155973","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc55779.2023.10155973","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.6700000166893005,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W107583932","https://openalex.org/W137538757","https://openalex.org/W1526654727","https://openalex.org/W1867103660","https://openalex.org/W2028145673","https://openalex.org/W2120678009","https://openalex.org/W2132908009","https://openalex.org/W2580909119","https://openalex.org/W2963412383","https://openalex.org/W2963872309","https://openalex.org/W2992629954","https://openalex.org/W2996795455","https://openalex.org/W3008801451","https://openalex.org/W3129266958","https://openalex.org/W3164258068","https://openalex.org/W4237591687","https://openalex.org/W4312072405","https://openalex.org/W4382936058","https://openalex.org/W6605726098","https://openalex.org/W6631500254","https://openalex.org/W6638503097","https://openalex.org/W6679661297","https://openalex.org/W6681960134","https://openalex.org/W6763257922","https://openalex.org/W6776530296","https://openalex.org/W6790621707","https://openalex.org/W6796019251","https://openalex.org/W6810170814"],"related_works":["https://openalex.org/W2092530219","https://openalex.org/W2388464034","https://openalex.org/W2533125852","https://openalex.org/W2140460949","https://openalex.org/W2105580438","https://openalex.org/W2057435755","https://openalex.org/W3121798572","https://openalex.org/W2018782216","https://openalex.org/W2770877918","https://openalex.org/W1989375655"],"abstract_inverted_index":{"Model-based":[0],"Reinforcement":[1],"Learning":[2],"(RL)":[3],"integrates":[4],"learning":[5,17],"and":[6,8,114],"planning":[7],"has":[9],"received":[10],"increasing":[11],"attention":[12],"in":[13,59,137],"recent":[14],"years.":[15],"However,":[16],"the":[18,32,50,57,68,71,93,101,104,108,111,115,123,145,149],"model":[19],"can":[20,132],"incur":[21],"a":[22,36,76,80,120,134,156],"significant":[23,135],"cost":[24],"(in":[25],"terms":[26,60],"of":[27,39,52,61,79,82,95,122,125],"sample":[28,63,138],"complexity),":[29],"due":[30],"to":[31,34,154],"need":[33],"obtain":[35],"sufficient":[37],"number":[38,81,124],"samples":[40],"for":[41],"each":[42],"state-action":[43],"pair.":[44],"In":[45],"this":[46],"paper,":[47],"we":[48,66],"investigate":[49],"benefits":[51],"leveraging":[53,141],"structural":[54,83,142],"information":[55,143],"about":[56,144],"system":[58,158],"reducing":[62],"complexity.":[64],"Specifically,":[65],"consider":[67,92],"setting":[69],"where":[70],"transition":[72],"probability":[73],"matrix":[74],"is":[75],"known":[77],"function":[78,121],"parameters,":[84],"whose":[85],"values":[86],"are":[87],"initially":[88],"unknown.":[89],"We":[90,106,147],"then":[91],"problem":[94],"estimating":[96],"those":[97],"parameters":[98],"based":[99],"on":[100],"interactions":[102],"with":[103,159],"environment.":[105],"characterize":[107],"difference":[109],"between":[110],"Q":[112,117],"estimates":[113],"optimal":[116],"value":[118],"as":[119],"samples.":[126],"Our":[127],"analysis":[128],"shows":[129],"that":[130],"there":[131],"be":[133],"saving":[136],"complexity":[139],"by":[140,151],"model.":[146],"illustrate":[148],"findings":[150],"considering":[152],"how":[153],"control":[155],"queuing":[157],"heterogeneous":[160],"servers.":[161]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}