{"id":"https://openalex.org/W4413918185","doi":"https://doi.org/10.1109/icra55743.2025.11128350","title":"SuPLE: Robot Learning with Lyapunov Rewards","display_name":"SuPLE: Robot Learning with Lyapunov Rewards","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413918185","doi":"https://doi.org/10.1109/icra55743.2025.11128350"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11128350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128350","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/A5108321683","display_name":"Phu Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I141720752","display_name":"Davidson College","ror":"https://ror.org/02f7k4z58","country_code":"US","type":"education","lineage":["https://openalex.org/I141720752"]},{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phu Nguyen","raw_affiliation_strings":["Davidson College of Engineering, San Jose State University,Computer Engineering Dept.,CA,USA,95192"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Davidson College of Engineering, San Jose State University,Computer Engineering Dept.,CA,USA,95192","institution_ids":["https://openalex.org/I141720752","https://openalex.org/I51504820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070558949","display_name":"Daniel Polani","orcid":"https://orcid.org/0000-0002-3233-5847"},"institutions":[{"id":"https://openalex.org/I141584323","display_name":"University of Hertfordshire","ror":"https://ror.org/0267vjk41","country_code":"GB","type":"education","lineage":["https://openalex.org/I141584323"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Daniel Polani","raw_affiliation_strings":["University of Hertfordshire,Department of Computer Science,UK,AL10 9AB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hertfordshire,Department of Computer Science,UK,AL10 9AB","institution_ids":["https://openalex.org/I141584323"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046771851","display_name":"Stas Tiomkin","orcid":"https://orcid.org/0000-0003-3677-6874"},"institutions":[{"id":"https://openalex.org/I12315562","display_name":"Texas Tech University","ror":"https://ror.org/0405mnx93","country_code":"US","type":"education","lineage":["https://openalex.org/I12315562"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stas Tiomkin","raw_affiliation_strings":["Texas Tech University,Department of Computer Science,TX,USA,79409"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Texas Tech University,Department of Computer Science,TX,USA,79409","institution_ids":["https://openalex.org/I12315562"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.19131938,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1177","last_page":"1183"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9904000163078308,"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":0.9904000163078308,"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":0.9890000224113464,"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/T10320","display_name":"Neural Networks and Applications","score":0.9751999974250793,"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/computer-science","display_name":"Computer science","score":0.6082432270050049},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6068218350410461},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.543524444103241},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4083143174648285},{"id":"https://openalex.org/keywords/control-theory","display_name":"Control theory (sociology)","score":0.40493112802505493},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.11095386743545532},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07704460620880127},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.0737210214138031}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6082432270050049},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6068218350410461},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.543524444103241},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4083143174648285},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.40493112802505493},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.11095386743545532},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07704460620880127},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0737210214138031},{"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/icra55743.2025.11128350","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11128350","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":[{"id":"https://openalex.org/G1802981795","display_name":null,"funder_award_id":"195-2020","funder_id":"https://openalex.org/F4320325704","funder_display_name":"PAZY Foundation"},{"id":"https://openalex.org/G6768408121","display_name":"CRII: RI: Interpretable Framework and Transformative Applications for Viability in Autonomous Agents","funder_award_id":"2246221","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320325704","display_name":"PAZY Foundation","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1591713425","https://openalex.org/W1786044565","https://openalex.org/W1997628743","https://openalex.org/W2041521369","https://openalex.org/W2062908485","https://openalex.org/W2106469529","https://openalex.org/W2111927824","https://openalex.org/W2124130071","https://openalex.org/W2152254020","https://openalex.org/W2156216606","https://openalex.org/W2169506284","https://openalex.org/W2726000386","https://openalex.org/W2898627204","https://openalex.org/W2911339327","https://openalex.org/W2995297712","https://openalex.org/W4300059230","https://openalex.org/W4319318414","https://openalex.org/W4382935740","https://openalex.org/W4400726681","https://openalex.org/W4401979752","https://openalex.org/W4408697061"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0,26],"reward":[1,49,197],"function":[2],"is":[3,35,84,140,149,261],"an":[4,57],"essential":[5],"component":[6],"in":[7,144,156,249],"robot":[8,146,176,239,247],"learning.":[9],"Reward":[10],"directly":[11],"affects":[12],"the":[13,21,41,44,61,65,76,79,89,101,122,126,138,173,178,191,202,214,219,227],"sample":[14],"and":[15,20,106,181,222,266],"computational":[16,98],"complexity":[17],"of":[18,23,28,43,64,78,91,103,116,193,216],"learning,":[19,147],"quality":[22],"a":[24,70,85,93,97,141,170,175,207,230,242],"solution.":[25],"design":[27,90],"informative":[29],"rewards":[30,237],"requires":[31],"domain":[32],"knowledge,":[33],"which":[34],"not":[36,183],"always":[37],"available.":[38],"We":[39,73,95],"use":[40,154],"properties":[42],"dynamics":[45,67],"to":[46,59,68,124,151,153,195,205,253],"produce":[47],"system-appropriate":[48],"without":[50,209],"adding":[51],"external":[52],"assumptions.":[53],"Specifically,":[54],"we":[55,199],"explore":[56],"approach":[58],"utilize":[60],"Lyapunov":[62,81],"exponents":[63],"system":[66],"generate":[69],"system-immanent":[71],"reward.":[72,94],"demonstrate":[74,107],"that":[75,201],"Sum":[77],"Positive":[80],"Exponents":[82],"(SuPLE)":[83],"strong":[86],"candidate":[87],"for":[88,100,113,213,233,238,245,264],"such":[92,168],"develop":[96],"framework":[99],"derivation":[102],"this":[104],"reward,":[105],"its":[108],"effectiveness":[109],"on":[110,177],"classical":[111],"benchmarks":[112],"sample-based":[114],"stabilization":[115],"various":[117],"dynamical":[118],"systems.":[119],"It":[120],"eliminates":[121],"need":[123],"start":[125,163],"training":[127],"trajectories":[128],"at":[129,172,187,226],"arbitrary":[130,188],"states,":[131],"also":[132],"known":[133],"as":[134,169,251],"auxiliary":[135,210],"exploration.":[136],"While":[137],"latter":[139,203],"common":[142],"practice":[143],"simulated":[145],"it":[148,155,224],"unpractical":[150],"consider":[152],"real":[157],"robotic":[158],"systems,":[159],"since":[160],"they":[161],"typically":[162],"from":[164],"natural":[165],"rest":[166],"states":[167],"pendulum":[171,221],"bottom,":[174],"ground,":[179],"etc.":[180],"can":[182],"be":[184],"easily":[185],"initialized":[186],"states.":[189],"Comparing":[190],"performance":[192],"SuPLE":[194],"commonly-used":[196],"functions,":[198],"observe":[200],"fail":[204],"find":[206],"solution":[208],"exploration,":[211],"even":[212],"task":[215],"swinging":[217],"up":[218],"double":[220],"keeping":[223],"stable":[225],"upright":[228],"position,":[229],"prototypical":[231],"scenario":[232],"multi-linked":[234],"robots.":[235],"SuPLE-induced":[236],"learning":[240,248],"offer":[241],"novel":[243],"route":[244],"effective":[246],"typical":[250],"opposed":[252],"highly":[254],"specialized":[255],"or":[256],"fine-tuned":[257],"scenarios.":[258],"Our":[259],"code":[260],"publicly":[262],"available":[263],"reproducibility":[265],"further":[267],"research.":[268]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}