{"id":"https://openalex.org/W4413393493","doi":"https://doi.org/10.23919/acc63710.2025.11107452","title":"Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning","display_name":"Decomposing Control Lyapunov Functions for Efficient Reinforcement Learning","publication_year":2025,"publication_date":"2025-07-08","ids":{"openalex":"https://openalex.org/W4413393493","doi":"https://doi.org/10.23919/acc63710.2025.11107452"},"language":"en","primary_location":{"id":"doi:10.23919/acc63710.2025.11107452","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5087248790","display_name":"Antonio M. L\u00f3pez","orcid":"https://orcid.org/0000-0002-6979-5783"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Antonio L\u00f3pez","raw_affiliation_strings":["University of Texas at Austin,Department of Aerospace Engineering and Engineering Mechanics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Department of Aerospace Engineering and Engineering Mechanics","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070827615","display_name":"David Fridovich-Keil","orcid":"https://orcid.org/0000-0002-5866-6441"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Fridovich-Keil","raw_affiliation_strings":["University of Texas at Austin,Department of Aerospace Engineering and Engineering Mechanics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Austin,Department of Aerospace Engineering and Engineering Mechanics","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.84456012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"180","last_page":"187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.98089998960495,"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":0.98089998960495,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.9165999889373779,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.9128000140190125,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7406525611877441},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.6107543706893921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6015284061431885},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5249978303909302},{"id":"https://openalex.org/keywords/lyapunov-redesign","display_name":"Lyapunov redesign","score":0.41699278354644775},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.4123609960079193},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35114961862564087},{"id":"https://openalex.org/keywords/lyapunov-exponent","display_name":"Lyapunov exponent","score":0.24251627922058105},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.08954581618309021}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7406525611877441},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.6107543706893921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6015284061431885},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5249978303909302},{"id":"https://openalex.org/C37935115","wikidata":"https://www.wikidata.org/wiki/Q6707085","display_name":"Lyapunov redesign","level":4,"score":0.41699278354644775},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.4123609960079193},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35114961862564087},{"id":"https://openalex.org/C191544260","wikidata":"https://www.wikidata.org/wiki/Q1238630","display_name":"Lyapunov exponent","level":3,"score":0.24251627922058105},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.08954581618309021},{"id":"https://openalex.org/C2777052490","wikidata":"https://www.wikidata.org/wiki/Q5072826","display_name":"Chaotic","level":2,"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:10.23919/acc63710.2025.11107452","is_oa":false,"landing_page_url":"https://doi.org/10.23919/acc63710.2025.11107452","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 American Control Conference (ACC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306113","display_name":"U.S. Department of State","ror":"https://ror.org/03vvynj75"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W329007756","https://openalex.org/W1582899597","https://openalex.org/W2018705428","https://openalex.org/W2041076275","https://openalex.org/W2061902782","https://openalex.org/W2117629901","https://openalex.org/W2476753885","https://openalex.org/W2807455070","https://openalex.org/W2907537824","https://openalex.org/W2918383326","https://openalex.org/W2951360122","https://openalex.org/W2963221646","https://openalex.org/W2963606896","https://openalex.org/W2964009453","https://openalex.org/W2964040381","https://openalex.org/W2968547875","https://openalex.org/W3038180127","https://openalex.org/W3109424835","https://openalex.org/W3174616316","https://openalex.org/W3184816927","https://openalex.org/W4280552001","https://openalex.org/W4313408211","https://openalex.org/W4406736214","https://openalex.org/W4411485043"],"related_works":["https://openalex.org/W2349796700","https://openalex.org/W1964805920","https://openalex.org/W3194517843","https://openalex.org/W3217133416","https://openalex.org/W2234502090","https://openalex.org/W4388874082","https://openalex.org/W2147929414","https://openalex.org/W2496188264","https://openalex.org/W2383986032","https://openalex.org/W2101859637"],"abstract_inverted_index":{"Recent":[0],"methods":[1,22,119],"using":[2],"Reinforcement":[3],"Learning":[4],"(RL)":[5],"have":[6],"proven":[7],"to":[8,28,34,41,55,92,104,113,120,128,203],"be":[9,162],"successful":[10],"for":[11,170],"training":[12],"intelligent":[13],"agents":[14],"in":[15,44,59,84,164,179],"unknown":[16],"environments.":[17],"However,":[18],"current":[19],"state-of-the-art":[20,220],"RL":[21,90,171,221],"require":[23,101],"large":[24],"amounts":[25],"of":[26,78,135,141,145,194,214],"data":[27,43,103,216],"learn":[29,93],"a":[30,52,79,114,122,142,183,201,206],"specific":[31],"task,":[32],"leading":[33],"unreasonable":[35],"costs":[36],"when":[37],"deploying":[38],"the":[39,76,85,132,139,165,192,212],"agent":[40],"collect":[42],"real-world":[45,215],"applications.":[46],"In":[47],"this":[48,108,195],"paper,":[49],"we":[50,68,149,190],"take":[51],"control-theoretic":[53],"approach":[54,62],"improve":[56],"sample":[57],"efficiency":[58],"RL.":[60],"Our":[61],"has":[63],"two":[64,219],"key":[65],"components.":[66],"First,":[67],"build":[69],"upon":[70],"recent":[71],"work":[72,137],"which":[73,148],"shows":[74],"that":[75,158],"inclusion":[77],"Control":[80,152],"Lyapunov":[81,153],"Function":[82],"(CLF)":[83],"reward":[86,172],"function":[87],"can":[88,161],"enable":[89],"algorithms":[91],"with":[94,208],"substantially":[95],"lower":[96],"discount":[97],"factors,":[98],"and":[99,117],"therefore":[100],"less":[102,209],"train.":[105],"To":[106],"do":[107,124],"\u201creward":[109],"shaping\u201d":[110],"requires":[111],"access":[112],"CLF,":[115],"however,":[116],"computational":[118],"compute":[121],"CLF":[123],"not":[125],"scale":[126],"well":[127],"high-dimensional":[129],"systems.":[130],"Therefore,":[131],"primary":[133],"contribution":[134],"our":[136,198],"is":[138],"development":[140],"new":[143],"variety":[144],"CLF-like":[146],"functions,":[147],"term":[150],"Decomposed":[151],"Functions":[154],"(DCLFs).":[155],"We":[156],"show":[157],"these":[159],"functions":[160],"used":[163],"same":[166],"way":[167],"as":[168],"CLFs":[169],"shaping,":[173],"yet":[174],"are":[175],"more":[176],"readily":[177],"computable":[178],"higher-dimensional":[180],"cases":[181],"via":[182],"system":[184],"decomposition":[185],"technique.":[186],"Through":[187],"multiple":[188],"examples,":[189],"demonstrate":[191],"effectiveness":[193],"approach,":[196],"where":[197],"method":[199],"finds":[200],"policy":[202],"successfully":[204],"land":[205],"quadcopter":[207],"than":[210],"half":[211],"amount":[213],"required":[217],"by":[218],"algorithms.":[222]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}