{"id":"https://openalex.org/W4407949575","doi":"https://doi.org/10.1109/cdc56724.2024.10886215","title":"Parametric PDE Control with Deep Reinforcement Learning and L<sub>0</sub> Sparse Polynomial Policies","display_name":"Parametric PDE Control with Deep Reinforcement Learning and L<sub>0</sub> Sparse Polynomial Policies","publication_year":2024,"publication_date":"2024-12-16","ids":{"openalex":"https://openalex.org/W4407949575","doi":"https://doi.org/10.1109/cdc56724.2024.10886215"},"language":"en","primary_location":{"id":"doi:10.1109/cdc56724.2024.10886215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","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/A5001000324","display_name":"Nicol\u00f2 Botteghi","orcid":"https://orcid.org/0000-0003-3676-3619"},"institutions":[{"id":"https://openalex.org/I94624287","display_name":"University of Twente","ror":"https://ror.org/006hf6230","country_code":"NL","type":"education","lineage":["https://openalex.org/I94624287"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"Nicol\u00f2 Botteghi","raw_affiliation_strings":["University of Twente,Department of Applied Mathematics,The Netherlands"],"affiliations":[{"raw_affiliation_string":"University of Twente,Department of Applied Mathematics,The Netherlands","institution_ids":["https://openalex.org/I94624287"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040035698","display_name":"Urban Fasel","orcid":"https://orcid.org/0000-0002-3716-686X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Urban Fasel","raw_affiliation_strings":["Imperial College London,Department of Aeronautics,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Aeronautics,United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001000324"],"corresponding_institution_ids":["https://openalex.org/I94624287"],"apc_list":null,"apc_paid":null,"fwci":0.6989,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.7379718,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6108","last_page":"6115"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10791","display_name":"Advanced Control Systems Optimization","score":0.6484000086784363,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.6484000086784363,"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/T14083","display_name":"Extremum Seeking Control Systems","score":0.5551999807357788,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8053985238075256},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.6050946712493896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5516020059585571},{"id":"https://openalex.org/keywords/polynomial","display_name":"Polynomial","score":0.5498523712158203},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5040522813796997},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4434754550457001},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.42066606879234314},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.29255425930023193},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.219917893409729},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14413121342658997},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.11496937274932861},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07219162583351135}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8053985238075256},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.6050946712493896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5516020059585571},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.5498523712158203},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5040522813796997},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4434754550457001},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.42066606879234314},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.29255425930023193},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.219917893409729},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14413121342658997},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.11496937274932861},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07219162583351135}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc56724.2024.10886215","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc56724.2024.10886215","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 63rd Conference on Decision and Control (CDC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W1820125862","https://openalex.org/W1977655452","https://openalex.org/W2005876975","https://openalex.org/W2013257838","https://openalex.org/W2032367183","https://openalex.org/W2145339207","https://openalex.org/W2145680191","https://openalex.org/W2239232218","https://openalex.org/W2395579298","https://openalex.org/W2484646121","https://openalex.org/W2499641798","https://openalex.org/W2522489477","https://openalex.org/W2566079294","https://openalex.org/W2575705757","https://openalex.org/W2580909119","https://openalex.org/W2589050007","https://openalex.org/W2768748954","https://openalex.org/W2786344118","https://openalex.org/W2787666871","https://openalex.org/W2809925683","https://openalex.org/W2962787969","https://openalex.org/W2963739154","https://openalex.org/W2975445440","https://openalex.org/W2996896271","https://openalex.org/W3009593063","https://openalex.org/W3014573904","https://openalex.org/W3021135564","https://openalex.org/W3086458503","https://openalex.org/W3088310808","https://openalex.org/W3090502885","https://openalex.org/W3100366369","https://openalex.org/W3100789280","https://openalex.org/W3183112146","https://openalex.org/W3215447930","https://openalex.org/W3216079546","https://openalex.org/W4206565284","https://openalex.org/W4220758675","https://openalex.org/W4231367092","https://openalex.org/W4255421341","https://openalex.org/W4311415873","https://openalex.org/W4321764793","https://openalex.org/W4392018457","https://openalex.org/W4392775038","https://openalex.org/W6631190155","https://openalex.org/W6635158341","https://openalex.org/W6635465357","https://openalex.org/W6637967152","https://openalex.org/W6677580257","https://openalex.org/W6677916085","https://openalex.org/W6678317597","https://openalex.org/W6684921986","https://openalex.org/W6685444567","https://openalex.org/W6713883836","https://openalex.org/W6729448088","https://openalex.org/W6730091202","https://openalex.org/W6732814185","https://openalex.org/W6733877748","https://openalex.org/W6741002519","https://openalex.org/W6747473740","https://openalex.org/W6748839928","https://openalex.org/W6771787661","https://openalex.org/W6773935107","https://openalex.org/W6776331362","https://openalex.org/W6790940118","https://openalex.org/W6842566449","https://openalex.org/W6858141428","https://openalex.org/W6862288241"],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W2379877967"],"abstract_inverted_index":{"Optimal":[0],"control":[1,40,58,75,83,121,189],"of":[2,41,64,95,160,182,185,197],"parametric":[3,42,124,163],"partial":[4],"differential":[5],"equations":[6,184],"(PDEs)":[7],"is":[8,130],"crucial":[9],"in":[10,13,29,60,140],"many":[11,79],"applications":[12],"engineering":[14],"and":[15,22,56,101,111,119,136,143,191],"science,":[16],"such":[17],"as":[18],"robotics,":[19],"aeronautics,":[20],"chemisty,":[21],"biomedicine.":[23],"In":[24,44,104],"recent":[25],"years,":[26],"the":[27,39,51,133,157,180,186,198,202],"progress":[28],"scientific":[30],"machine":[31],"learning":[32,48,110],"has":[33,50],"opened":[34],"up":[35],"new":[36],"frontiers":[37],"for":[38,78,123,179],"PDEs.":[43,125],"particular,":[45],"deep":[46,71],"reinforcement":[47],"(DRL)":[49],"potential":[52],"to":[53,86,115,132,194],"solve":[54],"high-dimensional":[55],"complex":[57],"problems":[59],"a":[61,162],"large":[62,93],"variety":[63],"applications.":[65],"Most":[66],"DRL":[67,134,145,175],"methods":[68],"rely":[69],"on":[70,156],"neural":[72],"network":[73],"(DNN)":[74],"policies.":[76,203],"However,":[77],"dynamical":[80],"systems,":[81],"DNN-based":[82,174],"policies":[84,122],"tend":[85],"be":[87,138],"over-parametrized,":[88],"which":[89],"means":[90],"they":[91],"need":[92],"amounts":[94],"training":[96],"data,":[97],"show":[98,167],"limited":[99],"robustness,":[100],"lack":[102],"interpretability.":[103],"this":[105],"work,":[106],"we":[107],"leverage":[108],"dictionary":[109],"differentiable":[112],"$L_{0}$":[113],"regularization":[114],"learn":[116],"sparse,":[117],"robust,":[118],"interpretable":[120,183],"Our":[126],"sparse":[127],"policy":[128],"architecture":[129],"agnostic":[131],"method":[135,170],"can":[137],"used":[139],"different":[141],"policy-gradient":[142],"actor-critic":[144],"algorithms":[146],"without":[147,200],"changing":[148],"their":[149],"policy-optimization":[150],"procedure.":[151],"We":[152,166],"test":[153],"our":[154,169],"approach":[155],"challenging":[158],"task":[159],"controlling":[161],"Kuramoto-Sivashinsky":[164],"PDE.":[165],"that":[168],"(1)":[171],"outperforms":[172],"baseline":[173],"policies,":[176],"(2)":[177],"allows":[178],"derivation":[181],"learned":[187],"optimal":[188],"laws,":[190],"(3)":[192],"generalizes":[193],"unseen":[195],"parameters":[196],"PDE":[199],"retraining":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}