{"id":"https://openalex.org/W4294691901","doi":"https://doi.org/10.23919/acc53348.2022.9867602","title":"Intermittent Reinforcement Learning with Sparse Rewards","display_name":"Intermittent Reinforcement Learning with Sparse Rewards","publication_year":2022,"publication_date":"2022-06-08","ids":{"openalex":"https://openalex.org/W4294691901","doi":"https://doi.org/10.23919/acc53348.2022.9867602"},"language":"en","primary_location":{"id":"doi:10.23919/acc53348.2022.9867602","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867602","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 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/A5043865100","display_name":"Prachi Pratyusha Sahoo","orcid":"https://orcid.org/0000-0002-2768-601X"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Prachi Pratyusha Sahoo","raw_affiliation_strings":["Georgia Institute of Technology,Woodruff School of Mechanical Engineering,Atlanta,GA,30332-0150"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Woodruff School of Mechanical Engineering,Atlanta,GA,30332-0150","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040301558","display_name":"Kyriakos G. Vamvoudakis","orcid":"https://orcid.org/0000-0003-1978-4848"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kyriakos G. Vamvoudakis","raw_affiliation_strings":["Georgia Institute of Technology,Daniel H. Guggenheim School of Aerospace Engineering,Atlanta,GA,30332-0150"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology,Daniel H. Guggenheim School of Aerospace Engineering,Atlanta,GA,30332-0150","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043865100"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.2594,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.38118812,"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":"2709","last_page":"2714"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9916999936103821,"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/T10675","display_name":"Mechanical Circulatory Support Devices","score":0.9585000276565552,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical 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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8930283188819885},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.643942654132843},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.4811231195926666},{"id":"https://openalex.org/keywords/time-horizon","display_name":"Time horizon","score":0.4779106080532074},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.47369384765625},{"id":"https://openalex.org/keywords/horizon","display_name":"Horizon","score":0.4692195653915405},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.437562495470047},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4049352705478668},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3341261148452759},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33193597197532654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21965870261192322}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8930283188819885},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.643942654132843},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.4811231195926666},{"id":"https://openalex.org/C28761237","wikidata":"https://www.wikidata.org/wiki/Q7805321","display_name":"Time horizon","level":2,"score":0.4779106080532074},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.47369384765625},{"id":"https://openalex.org/C159176650","wikidata":"https://www.wikidata.org/wiki/Q43261","display_name":"Horizon","level":2,"score":0.4692195653915405},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.437562495470047},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4049352705478668},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3341261148452759},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33193597197532654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21965870261192322},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/acc53348.2022.9867602","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc53348.2022.9867602","pdf_url":null,"source":{"id":"https://openalex.org/S4363607732","display_name":"2022 American Control Conference (ACC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2022 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1513689897","https://openalex.org/W1742307920","https://openalex.org/W1891098503","https://openalex.org/W1985235885","https://openalex.org/W1998922549","https://openalex.org/W2012173880","https://openalex.org/W2037031363","https://openalex.org/W2062175538","https://openalex.org/W2152161277","https://openalex.org/W2157076370","https://openalex.org/W2169239645","https://openalex.org/W2460713275","https://openalex.org/W2564717627","https://openalex.org/W2605628695","https://openalex.org/W2772589676","https://openalex.org/W2800330509","https://openalex.org/W3095852388","https://openalex.org/W3158799570","https://openalex.org/W3178463324","https://openalex.org/W3208486390","https://openalex.org/W4214717370","https://openalex.org/W4229706427"],"related_works":["https://openalex.org/W2906267174","https://openalex.org/W134501823","https://openalex.org/W2615656344","https://openalex.org/W2013239059","https://openalex.org/W2295626654","https://openalex.org/W4286622840","https://openalex.org/W2536121351","https://openalex.org/W2809608782","https://openalex.org/W2333245620","https://openalex.org/W1889576908"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"develop":[4],"a":[5,56],"control-design":[6],"framework":[7,69],"to":[8],"solve":[9],"the":[10,24,50,76,85,88],"optimal":[11],"control":[12],"problem":[13,33,42],"for":[14],"unknown":[15],"linear":[16],"time-invariant":[17],"systems":[18],"using":[19],"an":[20,37,62],"intermittent":[21,40,66],"approach":[22],"in":[23],"presence":[25],"of":[26,75,87],"sparse":[27,44,51],"and":[28,45,54,79],"dropped":[29,46],"reward":[30],"signals.":[31],"The":[32,68],"is":[34,70],"formulated":[35],"as":[36],"infinite":[38],"horizon":[39],"learning-based":[41],"with":[43,65,72],"reinforcements.":[47],"We":[48],"quantify":[49],"reinforcement":[52],"signals":[53],"provide":[55],"model-free":[57],"Q-learning":[58],"method":[59],"based":[60],"on":[61],"actor/critic":[63],"structure":[64],"updates.":[67],"provided":[71],"guaranteed":[73],"stability":[74],"closed-loop":[77],"system":[78],"optimality.":[80],"Finally,":[81],"simulation":[82],"results":[83],"show":[84],"efficacy":[86],"proposed":[89],"framework.":[90]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}