{"id":"https://openalex.org/W7123363542","doi":"https://doi.org/10.1109/cdc57313.2025.11312642","title":"Policy Gradient for LQR with Domain Randomization","display_name":"Policy Gradient for LQR with Domain Randomization","publication_year":2025,"publication_date":"2025-12-09","ids":{"openalex":"https://openalex.org/W7123363542","doi":"https://doi.org/10.1109/cdc57313.2025.11312642"},"language":null,"primary_location":{"id":"doi:10.1109/cdc57313.2025.11312642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th 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/A5008195425","display_name":"Tesshu Fujinami","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tesshu Fujinami","raw_affiliation_strings":["University of Pennsylvania,Department of Electrical and Systems Engineering"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Department of Electrical and Systems Engineering","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122901933","display_name":"Bruce D. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bruce D. Lee","raw_affiliation_strings":["University of Pennsylvania,Department of Electrical and Systems Engineering"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Department of Electrical and Systems Engineering","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052941508","display_name":"Nikolai Matni","orcid":"https://orcid.org/0000-0003-4936-3921"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolai Matni","raw_affiliation_strings":["University of Pennsylvania,Department of Electrical and Systems Engineering"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Department of Electrical and Systems Engineering","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122876024","display_name":"George J. Pappas","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George J. Pappas","raw_affiliation_strings":["University of Pennsylvania,Department of Electrical and Systems Engineering"],"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Department of Electrical and Systems Engineering","institution_ids":["https://openalex.org/I79576946"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5008195425"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":2.8599,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9440622,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4174","last_page":"4181"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.7911999821662903,"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":0.7911999821662903,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.03269999846816063,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.029400000348687172,"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/convergence","display_name":"Convergence (economics)","score":0.5945000052452087},{"id":"https://openalex.org/keywords/quadratic-equation","display_name":"Quadratic equation","score":0.5410000085830688},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5238000154495239},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4537999927997589},{"id":"https://openalex.org/keywords/linear-quadratic-regulator","display_name":"Linear-quadratic regulator","score":0.4196000099182129},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.3675999939441681},{"id":"https://openalex.org/keywords/rate-of-convergence","display_name":"Rate of convergence","score":0.32850000262260437},{"id":"https://openalex.org/keywords/stochastic-approximation","display_name":"Stochastic approximation","score":0.32010000944137573}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5644999742507935},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.557200014591217},{"id":"https://openalex.org/C129844170","wikidata":"https://www.wikidata.org/wiki/Q41299","display_name":"Quadratic equation","level":2,"score":0.5410000085830688},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4537999927997589},{"id":"https://openalex.org/C98779006","wikidata":"https://www.wikidata.org/wiki/Q2520550","display_name":"Linear-quadratic regulator","level":3,"score":0.4196000099182129},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.37439998984336853},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.3675999939441681},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.32850000262260437},{"id":"https://openalex.org/C55479107","wikidata":"https://www.wikidata.org/wiki/Q97663916","display_name":"Stochastic approximation","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C81299745","wikidata":"https://www.wikidata.org/wiki/Q334269","display_name":"Transfer function","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C2780813799","wikidata":"https://www.wikidata.org/wiki/Q3274237","display_name":"Zero (linguistics)","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C115680565","wikidata":"https://www.wikidata.org/wiki/Q5977448","display_name":"Gradient method","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C28826006","wikidata":"https://www.wikidata.org/wiki/Q33521","display_name":"Applied mathematics","level":1,"score":0.2524999976158142}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cdc57313.2025.11312642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cdc57313.2025.11312642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 64th 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":13,"referenced_works":["https://openalex.org/W1987656566","https://openalex.org/W2069037813","https://openalex.org/W2132922421","https://openalex.org/W2167412190","https://openalex.org/W2605102758","https://openalex.org/W2767050701","https://openalex.org/W2982095652","https://openalex.org/W2997854628","https://openalex.org/W3209135762","https://openalex.org/W3212380917","https://openalex.org/W4250954493","https://openalex.org/W4367841446","https://openalex.org/W7123363542"],"related_works":[],"abstract_inverted_index":{"Domain":[0],"randomization":[1],"(DR)":[2],"enables":[3],"sim-to-real":[4],"transfer":[5],"by":[6],"training":[7],"controllers":[8],"on":[9,89],"a":[10,79,104,119],"distribution":[11],"of":[12,18,44,60,78,82,92],"simulated":[13],"environments,":[14],"with":[15,102],"the":[16,23,56,76,83,90,93,99,109,125],"goal":[17],"achieving":[19,103],"robust":[20],"performance":[21,106],"in":[22,31],"real":[24],"world.":[25],"Although":[26],"DR":[27,84,154],"is":[28,34],"widely":[29],"used":[30],"practice":[32],"and":[33,111,117,145,156],"often":[35],"solved":[36],"using":[37],"simple":[38],"policy":[39],"gradient":[40],"(PG)":[41],"methods,":[42],"understanding":[43],"its":[45],"theoretical":[46,143],"guarantees":[47],"remains":[48],"limited.":[49],"Toward":[50],"addressing":[51],"this":[52],"gap,":[53],"we":[54,115],"provide":[55],"first":[57],"convergence":[58],"analysis":[59],"PG":[61,72,158],"methods":[62],"for":[63,127,149],"domain-randomized":[64],"linear":[65],"quadratic":[66],"regulator":[67],"(LQR).":[68],"We":[69,96],"show":[70],"that":[71,123],"converges":[73],"globally":[74],"to":[75,137],"minimizer":[77],"finite-sample":[80],"approximation":[81],"objective":[85],"under":[86],"suitable":[87],"bounds":[88],"heterogeneity":[91],"sampled":[94],"systems.":[95],"also":[97],"quantify":[98],"sample-complexity":[100],"associated":[101],"small":[105],"gap":[107],"between":[108],"sample-average":[110],"population-level":[112],"objectives.":[113],"Additionally,":[114],"propose":[116],"analyze":[118],"discount-factor":[120],"annealing":[121],"algorithm":[122],"obviates":[124],"need":[126],"an":[128],"initial":[129],"jointly":[130],"stabilizing":[131],"controller,":[132],"which":[133],"may":[134],"be":[135],"challenging":[136],"find.":[138],"Empirical":[139],"results":[140],"support":[141],"our":[142],"findings":[144],"highlight":[146],"promising":[147],"directions":[148],"future":[150],"work,":[151],"including":[152],"risk-sensitive":[153],"formulations":[155],"stochastic":[157],"algorithms.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-14T00:46:21.520733","created_date":"2026-01-14T00:00:00"}