{"id":"https://openalex.org/W4413925340","doi":"https://doi.org/10.1109/icra55743.2025.11128069","title":"Neural Lyapunov Function Approximation with Self-Supervised Reinforcement Learning","display_name":"Neural Lyapunov Function Approximation with Self-Supervised Reinforcement Learning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413925340","doi":"https://doi.org/10.1109/icra55743.2025.11128069"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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/A5037542595","display_name":"Luc McCutcheon","orcid":null},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Luc McCutcheon","raw_affiliation_strings":["University of Surrey,CAV-Lab,Department of Mechanical Engineering Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,CAV-Lab,Department of Mechanical Engineering Sciences","institution_ids":["https://openalex.org/I28290843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022064746","display_name":"Bahman Gharesifard","orcid":"https://orcid.org/0000-0003-1495-3489"},"institutions":[{"id":"https://openalex.org/I161318765","display_name":"University of California, Los Angeles","ror":"https://ror.org/046rm7j60","country_code":"US","type":"education","lineage":["https://openalex.org/I161318765"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bahman Gharesifard","raw_affiliation_strings":["University of California,Department of Electrical and Computer Engineering,Los Angeles"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Department of Electrical and Computer Engineering,Los Angeles","institution_ids":["https://openalex.org/I161318765"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071227510","display_name":"Saber Fallah","orcid":"https://orcid.org/0000-0002-1298-1040"},"institutions":[{"id":"https://openalex.org/I28290843","display_name":"University of Surrey","ror":"https://ror.org/00ks66431","country_code":"GB","type":"education","lineage":["https://openalex.org/I28290843"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Saber Fallah","raw_affiliation_strings":["University of Surrey,CAV-Lab,Department of Mechanical Engineering Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Surrey,CAV-Lab,Department of Mechanical Engineering Sciences","institution_ids":["https://openalex.org/I28290843"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19189891,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1170","last_page":"1176"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9763000011444092,"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/T10320","display_name":"Neural Networks and Applications","score":0.9763000011444092,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9068999886512756,"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":0.7347569465637207},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.6395775675773621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5988967418670654},{"id":"https://openalex.org/keywords/function-approximation","display_name":"Function approximation","score":0.48683708906173706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4564081132411957},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4514332413673401},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45055249333381653},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.09855672717094421},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.09507250785827637}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7347569465637207},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.6395775675773621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5988967418670654},{"id":"https://openalex.org/C91873725","wikidata":"https://www.wikidata.org/wiki/Q3445816","display_name":"Function approximation","level":3,"score":0.48683708906173706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4564081132411957},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4514332413673401},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45055249333381653},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.09855672717094421},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09507250785827637},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11128069","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128069","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","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":14,"referenced_works":["https://openalex.org/W1483660345","https://openalex.org/W1496681274","https://openalex.org/W2524522145","https://openalex.org/W2951360122","https://openalex.org/W2968945909","https://openalex.org/W2996975825","https://openalex.org/W3045059767","https://openalex.org/W3156919398","https://openalex.org/W4206497039","https://openalex.org/W4210390142","https://openalex.org/W4285601030","https://openalex.org/W4315489198","https://openalex.org/W4385626915","https://openalex.org/W4391020011"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W3021988786","https://openalex.org/W2380199044","https://openalex.org/W3099311996"],"abstract_inverted_index":{"Control":[0],"Lyapunov":[1,40,71,99],"functions":[2,20,72],"are":[3],"traditionally":[4],"used":[5],"to":[6,13,47,69,95],"design":[7],"a":[8,14,25,31,65],"controller":[9],"which":[10],"ensures":[11],"convergence":[12,89],"desired":[15],"state,":[16],"yet":[17],"deriving":[18],"these":[19],"for":[21,35,53],"nonlinear":[22,39],"systems":[23],"remains":[24],"complex":[26],"challenge.":[27],"This":[28],"paper":[29],"presents":[30],"novel,":[32],"sample-efficient":[33],"method":[34,77],"neural":[36,98],"approximation":[37,92,100],"of":[38,57],"functions,":[41],"leveraging":[42],"self-supervised":[43],"Reinforcement":[44],"Learning":[45],"(RL)":[46],"enhance":[48],"training":[49],"data":[50],"generation,":[51],"particularly":[52],"inaccurately":[54],"represented":[55],"regions":[56],"the":[58,96],"state":[59],"space.":[60],"The":[61,76,102],"proposed":[62],"approach":[63],"employs":[64],"data-driven":[66],"World":[67],"Model":[68],"train":[70],"from":[73],"off-policy":[74],"trajectories.":[75],"is":[78,104],"validated":[79],"on":[80],"both":[81],"standard":[82],"and":[83,90],"goal-conditioned":[84],"robotic":[85],"tasks,":[86],"demonstrating":[87],"faster":[88],"higher":[91],"accuracy":[93],"compared":[94],"state-of-the-art":[97],"baseline.":[101],"code":[103],"available":[105],"at:":[106],"https://github.com/CAV-Research-Lab/SACLA.git":[107]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}