{"id":"https://openalex.org/W34013550","doi":null,"title":"Lyapunov-Constrained Action Sets for Reinforcement Learning","display_name":"Lyapunov-Constrained Action Sets for Reinforcement Learning","publication_year":2001,"publication_date":"2001-06-28","ids":{"openalex":"https://openalex.org/W34013550","mag":"34013550"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.1279","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.1279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-anw.cs.umass.edu/~perkins/LyRL.ps","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5009680404","display_name":"Theodore J. Perkins","orcid":"https://orcid.org/0000-0002-6622-8003","observed_orcids":["https://orcid.org/0000-0002-6622-8003"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Theodore J. Perkins","raw_affiliation_strings":["University of Massachusetts: Amherst#TAB#"],"raw_orcid":"https://orcid.org/0000-0002-6622-8003","affiliations":[{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089808068","display_name":"Andrew G. Barto","orcid":"https://orcid.org/0000-0002-3581-1896","observed_orcids":["https://orcid.org/0000-0002-3581-1896"]},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew G. Barto","raw_affiliation_strings":["University of Massachusetts: Amherst#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts: Amherst#TAB#","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":1.7209,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.85762775,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"409","last_page":"416"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":1.0,"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":1.0,"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":0.00019999999494757503,"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/T10791","display_name":"Advanced Control Systems Optimization","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.9139999747276306},{"id":"https://openalex.org/keywords/action-sets","display_name":"action sets","score":0.6650000214576721},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.8479999899864197},{"id":"https://openalex.org/keywords/stability-guarantees","display_name":"stability guarantees","score":0.47600001096725464},{"id":"https://openalex.org/keywords/robust-control","display_name":"robust control","score":0.6380000114440918},{"id":"https://openalex.org/keywords/industrial-robots","display_name":"industrial robots","score":0.5879999995231628},{"id":"https://openalex.org/keywords/pendulum-swing-up","display_name":"pendulum swing-up","score":0.984000027179718},{"id":"https://openalex.org/keywords/robotic-arm-control","display_name":"robotic arm control","score":0.906000018119812},{"id":"https://openalex.org/keywords/accelerated-learning","display_name":"accelerated learning","score":0.7450000047683716}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7650606632232666},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.7490556836128235},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6481475830078125},{"id":"https://openalex.org/C192921069","wikidata":"https://www.wikidata.org/wiki/Q550134","display_name":"Inverted pendulum","level":3,"score":0.5794589519500732},{"id":"https://openalex.org/C201030206","wikidata":"https://www.wikidata.org/wiki/Q5165805","display_name":"Control-Lyapunov function","level":5,"score":0.5621969103813171},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.531231701374054},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.517379879951477},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.46419110894203186},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.44660359621047974},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.442632257938385},{"id":"https://openalex.org/C37935115","wikidata":"https://www.wikidata.org/wiki/Q6707085","display_name":"Lyapunov redesign","level":4,"score":0.43432843685150146},{"id":"https://openalex.org/C2776829284","wikidata":"https://www.wikidata.org/wiki/Q1341651","display_name":"Lyapunov stability","level":3,"score":0.41282257437705994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29463040828704834},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.28866857290267944},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25499653816223145},{"id":"https://openalex.org/C191544260","wikidata":"https://www.wikidata.org/wiki/Q1238630","display_name":"Lyapunov exponent","level":3,"score":0.2116897702217102},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15775471925735474},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.1279","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.1279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-anw.cs.umass.edu/~perkins/LyRL.ps","raw_type":"text"},{"id":"mag:34013550","doi":null,"is_oa":false,"landing_page_url":"https://dblp.uni-trier.de/db/conf/icml/icml2001.html#PerkinsB01","pdf_url":null,"source":{"id":"https://openalex.org/S4306419644","display_name":"International Conference on Machine Learning","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"International Conference on Machine Learning","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G2899210720","display_name":null,"funder_award_id":"No. 295292","funder_id":"https://openalex.org/F4320322245","funder_display_name":"Isfahan University of Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320322245","display_name":"Isfahan University of Medical Sciences","ror":"https://ror.org/04waqzz56"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W24473057","https://openalex.org/W79229537","https://openalex.org/W1531261160","https://openalex.org/W1568042657","https://openalex.org/W1585861384","https://openalex.org/W1589064538","https://openalex.org/W1591803298","https://openalex.org/W1598593415","https://openalex.org/W1777239053","https://openalex.org/W1964157254","https://openalex.org/W1971140944","https://openalex.org/W1976295103","https://openalex.org/W1983133896","https://openalex.org/W1994380514","https://openalex.org/W2041367235","https://openalex.org/W2044447001","https://openalex.org/W2062691475","https://openalex.org/W2070301851","https://openalex.org/W2090167557","https://openalex.org/W2104245950","https://openalex.org/W2110144538","https://openalex.org/W2121517924","https://openalex.org/W2121863487","https://openalex.org/W2124175081","https://openalex.org/W2128683199","https://openalex.org/W2131398727","https://openalex.org/W2133473556","https://openalex.org/W2142225512","https://openalex.org/W2149398074","https://openalex.org/W2169961654","https://openalex.org/W2233281638","https://openalex.org/W2297459312","https://openalex.org/W2325521596","https://openalex.org/W2396339611","https://openalex.org/W2622020362","https://openalex.org/W2741793312","https://openalex.org/W2791293611","https://openalex.org/W2793244142","https://openalex.org/W2802441274","https://openalex.org/W2884665637","https://openalex.org/W2922939232","https://openalex.org/W2981781241","https://openalex.org/W2991596591","https://openalex.org/W3011120880","https://openalex.org/W3012607842","https://openalex.org/W3017330209","https://openalex.org/W3035020267"],"related_works":["https://openalex.org/W2473480709","https://openalex.org/W7171920923","https://openalex.org/W181569489","https://openalex.org/W2342231971","https://openalex.org/W4293152345","https://openalex.org/W2803543472","https://openalex.org/W7201927806","https://openalex.org/W1604599080","https://openalex.org/W4292103799","https://openalex.org/W2913300629"],"abstract_inverted_index":{"Lyapunov":[0,34,112],"analysis":[1],"is":[2,115],"a":[3,24,33,52],"standard":[4],"approach":[5,149],"to":[6,14,19,29,92,103],"studying":[7],"the":[8,21,42,48,60,90,132,147],"stability":[9],"of":[10,23,45,59,85,128,134],"dynamical":[11],"systems":[12,107,137],"and":[13,76,79,141,157],"designing":[15],"controllers.":[16],"We":[17,145],"propose":[18],"design":[20],"actions":[22,87],"reinforcement":[25],"learning":[26,72],"(RL)":[27],"agent":[28,49,96],"be":[30],"descending":[31],"on":[32,55,150],"function.":[35],"For":[36],"minimum":[37],"cost-to-target":[38],"problems,":[39,129],"this":[40,83],"has":[41],"theoretical":[43],"benefit":[44],"guaranteeing":[46],"that":[47],"will":[50],"reach":[51],"goal":[53],"state":[54],"every":[56],"trial,":[57],"regardless":[58],"RL":[61,95,106],"algorithm":[62],"it":[63,100],"uses.":[64],"In":[65],"practice,":[66],"Lyapunov-descent":[67],"constraints":[68],"can":[69,97],"significantly":[70],"shorten":[71],"trials,":[73],"improve":[74],"initial":[75],"worst-case":[77],"performance,":[78],"accelerate":[80],"learning.":[81],"Although":[82],"method":[84],"constraining":[86],"may":[88],"limit":[89],"extent":[91],"which":[93,111],"an":[94],"minimize":[98],"cost,":[99],"allows":[101],"one":[102],"construct":[104],"robust":[105],"for":[108],"problems":[109,122],"in":[110],"domain":[113],"knowledge":[114],"available.":[116],"This":[117],"includes":[118],"many":[119],"important":[120],"individual":[121],"as":[123,125,131],"well":[124],"general":[126,148],"classes":[127],"such":[130],"control":[133,153],"feedback":[135],"linearizable":[136],"(e.g.,":[138],"industrial":[139],"robots)":[140],"continuous-state":[142],"path-planning":[143],"problems.":[144],"demonstrate":[146],"two":[151],"simulated":[152],"problems:":[154],"pendulum":[155],"swing-up":[156],"robot":[158],"arm":[159],"control.":[160],"1.":[161]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}