{"id":"https://openalex.org/W4383108297","doi":"https://doi.org/10.1109/icra48891.2023.10160928","title":"Learning Stabilization Control from Observations by Learning Lyapunov-like Proxy Models","display_name":"Learning Stabilization Control from Observations by Learning Lyapunov-like Proxy Models","publication_year":2023,"publication_date":"2023-05-29","ids":{"openalex":"https://openalex.org/W4383108297","doi":"https://doi.org/10.1109/icra48891.2023.10160928"},"language":"en","primary_location":{"id":"doi:10.1109/icra48891.2023.10160928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","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/A5031297903","display_name":"Milan Ganai","orcid":"https://orcid.org/0009-0001-1825-3650"},"institutions":[{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]},{"id":"https://openalex.org/I160856358","display_name":"University of San Diego","ror":"https://ror.org/03jbbze48","country_code":"US","type":"education","lineage":["https://openalex.org/I160856358"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Milan Ganai","raw_affiliation_strings":["UC San Diego,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, UC San Diego, USA"],"affiliations":[{"raw_affiliation_string":"UC San Diego,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I2800935791","https://openalex.org/I160856358"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, UC San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071243077","display_name":"C Hirayama","orcid":null},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]},{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I160856358","display_name":"University of San Diego","ror":"https://ror.org/03jbbze48","country_code":"US","type":"education","lineage":["https://openalex.org/I160856358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chiaki Hirayama","raw_affiliation_strings":["UC San Diego,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, UC San Diego, USA"],"affiliations":[{"raw_affiliation_string":"UC San Diego,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I2800935791","https://openalex.org/I160856358"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, UC San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034281181","display_name":"Ya-Chien Chang","orcid":"https://orcid.org/0000-0003-3497-7971"},"institutions":[{"id":"https://openalex.org/I160856358","display_name":"University of San Diego","ror":"https://ror.org/03jbbze48","country_code":"US","type":"education","lineage":["https://openalex.org/I160856358"]},{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ya-Chien Chang","raw_affiliation_strings":["UC San Diego,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, UC San Diego, USA"],"affiliations":[{"raw_affiliation_string":"UC San Diego,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I2800935791","https://openalex.org/I160856358"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, UC San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081085178","display_name":"Sicun Gao","orcid":"https://orcid.org/0000-0003-2524-4960"},"institutions":[{"id":"https://openalex.org/I2800935791","display_name":"UC San Diego Health System","ror":"https://ror.org/01kbfgm16","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I2800935791"]},{"id":"https://openalex.org/I36258959","display_name":"University of California, San Diego","ror":"https://ror.org/0168r3w48","country_code":"US","type":"education","lineage":["https://openalex.org/I36258959"]},{"id":"https://openalex.org/I160856358","display_name":"University of San Diego","ror":"https://ror.org/03jbbze48","country_code":"US","type":"education","lineage":["https://openalex.org/I160856358"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sicun Gao","raw_affiliation_strings":["UC San Diego,Department of Computer Science and Engineering,USA","Department of Computer Science and Engineering, UC San Diego, USA"],"affiliations":[{"raw_affiliation_string":"UC San Diego,Department of Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I2800935791","https://openalex.org/I160856358"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, UC San Diego, USA","institution_ids":["https://openalex.org/I36258959"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031297903"],"corresponding_institution_ids":["https://openalex.org/I160856358","https://openalex.org/I2800935791","https://openalex.org/I36258959"],"apc_list":null,"apc_paid":null,"fwci":0.6993,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74925116,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2913","last_page":"2920"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9927999973297119,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9902999997138977,"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":0.6902849078178406},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6785938739776611},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5960816144943237},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5900211334228516},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5874881148338318},{"id":"https://openalex.org/keywords/proxy","display_name":"Proxy (statistics)","score":0.5697644948959351},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5651963353157043},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.5599690079689026},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.47025740146636963},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4688008427619934},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4605158567428589},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4580487310886383},{"id":"https://openalex.org/keywords/kinematics","display_name":"Kinematics","score":0.4503744840621948},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4162661135196686},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17759960889816284}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6902849078178406},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6785938739776611},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5960816144943237},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5900211334228516},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5874881148338318},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.5697644948959351},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5651963353157043},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.5599690079689026},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47025740146636963},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4688008427619934},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4605158567428589},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4580487310886383},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.4503744840621948},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4162661135196686},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17759960889816284},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra48891.2023.10160928","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra48891.2023.10160928","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4895191527","display_name":null,"funder_award_id":"FA8750-18-C-0092","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G954480827","display_name":null,"funder_award_id":"FA9550-19-1-0041","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"}],"funders":[{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":55,"referenced_works":["https://openalex.org/W1569657508","https://openalex.org/W1986014385","https://openalex.org/W1991667713","https://openalex.org/W1999874108","https://openalex.org/W2016765487","https://openalex.org/W2121863487","https://openalex.org/W2129202194","https://openalex.org/W2158782408","https://openalex.org/W2167224731","https://openalex.org/W2174803659","https://openalex.org/W2409942531","https://openalex.org/W2462906003","https://openalex.org/W2529658650","https://openalex.org/W2559655401","https://openalex.org/W2591283724","https://openalex.org/W2604382266","https://openalex.org/W2606411279","https://openalex.org/W2736601468","https://openalex.org/W2743603832","https://openalex.org/W2799729333","https://openalex.org/W2884247313","https://openalex.org/W2889315996","https://openalex.org/W2899184737","https://openalex.org/W2913300629","https://openalex.org/W2952854274","https://openalex.org/W2962787969","https://openalex.org/W2962845991","https://openalex.org/W2964460729","https://openalex.org/W2971979296","https://openalex.org/W2990138404","https://openalex.org/W3045059767","https://openalex.org/W3112804989","https://openalex.org/W3130800560","https://openalex.org/W3159659315","https://openalex.org/W3207110310","https://openalex.org/W4213251304","https://openalex.org/W4247664601","https://openalex.org/W6634230617","https://openalex.org/W6679048878","https://openalex.org/W6680724558","https://openalex.org/W6684338915","https://openalex.org/W6718092244","https://openalex.org/W6718836005","https://openalex.org/W6741002519","https://openalex.org/W6751526458","https://openalex.org/W6751535212","https://openalex.org/W6753770476","https://openalex.org/W6754484421","https://openalex.org/W6755802134","https://openalex.org/W6756714161","https://openalex.org/W6758924645","https://openalex.org/W6763078103","https://openalex.org/W6767277667","https://openalex.org/W6767341937","https://openalex.org/W6785775855"],"related_works":["https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4229499248","https://openalex.org/W2566006169","https://openalex.org/W1567818861","https://openalex.org/W2987774938","https://openalex.org/W4256492088","https://openalex.org/W632915154","https://openalex.org/W2055733372","https://openalex.org/W3022067003"],"abstract_inverted_index":{"The":[0,89],"deployment":[1],"of":[2,11,31,52,56,86,167],"Reinforcement":[3],"Learning":[4,23],"to":[5,58,93,106,119],"robotics":[6],"applications":[7],"faces":[8],"the":[9,29,49,70,73,111,115,123,132,178],"difficulty":[10],"reward":[12,20,67],"engineering.":[13],"Therefore,":[14],"approaches":[15,175],"have":[16],"focused":[17],"on":[18,77],"creating":[19],"functions":[21,68],"by":[22,60],"from":[24,34,100],"Observations":[25],"(LfO)":[26],"which":[27],"is":[28],"task":[30],"learning":[32,57,129],"policies":[33],"expert":[35,71,101,186],"trajectories":[36],"that":[37,135],"only":[38],"contain":[39],"state":[40,102],"sequences.":[41],"We":[42,126,142,171],"propose":[43],"new":[44],"methods":[45,145,180],"for":[46,48,131,138],"LfO":[47,82],"important":[50,137],"class":[51],"continuous":[53],"control":[54,155,162],"problems":[55,156],"stabilize,":[59],"introducing":[61],"intermediate":[62],"proxy":[63,98],"models":[64],"acting":[65],"as":[66],"between":[69],"and":[72,110,151,163,176],"agent":[74],"policy":[75],"based":[76],"Lyapunov":[78],"stability":[79],"theory.":[80],"Our":[81],"training":[83,122,140],"process":[84],"consists":[85],"two":[87,133],"steps.":[88],"first":[90],"step":[91,113],"attempts":[92],"learn":[94,182],"a":[95],"Lyapunov-like":[96],"landscape":[97,117],"model":[99,118],"sequences":[103],"without":[104],"access":[105],"any":[107],"kinematics":[108],"model,":[109],"second":[112],"uses":[114],"learned":[116],"guide":[120],"in":[121,146,157,169],"learner's":[124],"policy.":[125],"formulate":[127],"novel":[128],"objectives":[130],"steps":[134],"are":[136],"overall":[139],"success.":[141],"evaluate":[143],"our":[144],"real":[147],"automobile":[148],"robot":[149],"environments":[150],"other":[152],"simulated":[153],"stabilization":[154],"model-free":[158],"settings,":[159],"like":[160],"Quadrotor":[161],"maintaining":[164],"upright":[165],"positions":[166],"Hopper":[168],"MuJoCo.":[170],"compare":[172],"with":[173,184],"state-of-the-art":[174],"show":[177],"proposed":[179],"can":[181],"efficiently":[183],"less":[185],"observations.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}