{"id":"https://openalex.org/W3212756799","doi":"https://doi.org/10.1109/systol52990.2021.9595754","title":"Transfer reinforcement learning for fault-tolerant control by re-using optimal policies","display_name":"Transfer reinforcement learning for fault-tolerant control by re-using optimal policies","publication_year":2021,"publication_date":"2021-09-29","ids":{"openalex":"https://openalex.org/W3212756799","doi":"https://doi.org/10.1109/systol52990.2021.9595754","mag":"3212756799"},"language":"en","primary_location":{"id":"doi:10.1109/systol52990.2021.9595754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/systol52990.2021.9595754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 5th International Conference on Control and Fault-Tolerant Systems (SysTol)","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/A5103746138","display_name":"Ibrahim Ahmed","orcid":"https://orcid.org/0009-0003-2113-3910"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ibrahim Ahmed","raw_affiliation_strings":["Vanderbilt University"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035863735","display_name":"Marcos Qui\u00f1ones-Grueiro","orcid":"https://orcid.org/0000-0001-5391-6774"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marcos Quinones-Grueiro","raw_affiliation_strings":["Vanderbilt University"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051150754","display_name":"Gautam Biswas","orcid":"https://orcid.org/0000-0002-2752-3878"},"institutions":[{"id":"https://openalex.org/I200719446","display_name":"Vanderbilt University","ror":"https://ror.org/02vm5rt34","country_code":"US","type":"education","lineage":["https://openalex.org/I200719446"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Biswas","raw_affiliation_strings":["Vanderbilt University"],"affiliations":[{"raw_affiliation_string":"Vanderbilt University","institution_ids":["https://openalex.org/I200719446"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103746138"],"corresponding_institution_ids":["https://openalex.org/I200719446"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16618373,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"99","issue":null,"first_page":"25","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.9979000091552734,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9979000091552734,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9937000274658203,"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":0.9936000108718872,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8341394662857056},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.8147773742675781},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7069492936134338},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6617864966392517},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5844801068305969},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.5533671379089355},{"id":"https://openalex.org/keywords/consolidation","display_name":"Consolidation (business)","score":0.5077387094497681},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4682164192199707},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.4572370648384094},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.4251343607902527},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.42009884119033813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38968807458877563},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3349847197532654},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.295306533575058},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.21014150977134705}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8341394662857056},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.8147773742675781},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7069492936134338},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6617864966392517},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5844801068305969},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.5533671379089355},{"id":"https://openalex.org/C2776014549","wikidata":"https://www.wikidata.org/wiki/Q3050847","display_name":"Consolidation (business)","level":2,"score":0.5077387094497681},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4682164192199707},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.4572370648384094},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.4251343607902527},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.42009884119033813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38968807458877563},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3349847197532654},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.295306533575058},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.21014150977134705},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/systol52990.2021.9595754","is_oa":false,"landing_page_url":"https://doi.org/10.1109/systol52990.2021.9595754","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 5th International Conference on Control and Fault-Tolerant Systems (SysTol)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W1579424694","https://openalex.org/W1646707810","https://openalex.org/W1757796397","https://openalex.org/W1971115921","https://openalex.org/W2032561264","https://openalex.org/W2040169580","https://openalex.org/W2102997946","https://openalex.org/W2125074935","https://openalex.org/W2155027007","https://openalex.org/W2326192517","https://openalex.org/W2341171179","https://openalex.org/W2736601468","https://openalex.org/W2949859465","https://openalex.org/W3023586494","https://openalex.org/W3085267010","https://openalex.org/W3085941049","https://openalex.org/W3091635810","https://openalex.org/W3096211637","https://openalex.org/W3124696433","https://openalex.org/W3155597816","https://openalex.org/W4237591687","https://openalex.org/W4298857966","https://openalex.org/W6637967152","https://openalex.org/W6675670748","https://openalex.org/W6678545291","https://openalex.org/W6683204974","https://openalex.org/W6741002519","https://openalex.org/W6783144354"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W3095877357","https://openalex.org/W183202219","https://openalex.org/W10861731","https://openalex.org/W2072565696","https://openalex.org/W4386121542"],"abstract_inverted_index":{"This":[0],"paper":[1],"develops":[2],"a":[3,7,15,43,77,80],"transfer-learning":[4],"approach":[5,21,68,75],"in":[6,36,51],"reinforcement":[8],"learning":[9,29],"framework":[10],"for":[11,57],"fault-tolerant":[12],"control":[13],"of":[14,17,54,79,85],"class":[16],"dynamical":[18],"systems.":[19],"Our":[20,39],"combines":[22],"policy-reuse":[23,40],"and":[24,71],"consolidation":[25],"algorithms":[26],"to":[27],"achieve":[28],"speed":[30],"improvement":[31],"when":[32],"new":[33],"faults":[34],"occur":[35],"the":[37,52,63],"system.":[38],"strategy":[41],"finds":[42],"policy":[44],"parameter":[45],"initialization":[46],"that":[47],"leverages":[48],"previous":[49],"knowledge":[50],"form":[53],"learned":[55],"policies":[56],"past":[58],"fault":[59],"occurrences.":[60],"We":[61],"present":[62],"conditions":[64],"under":[65],"which":[66],"our":[67,74],"becomes":[69],"effective":[70],"empirically":[72],"demonstrate":[73],"on":[76],"test-bed":[78],"6-tank":[81],"fuel":[82],"transfer":[83],"system":[84],"an":[86],"aircraft.":[87]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
