{"id":"https://openalex.org/W4407809681","doi":"https://doi.org/10.3233/978-1-60750-754-3-70","title":"Safe Reinforcement Learning for Continuous Spaces through Lyapunov-Constrained Behavior","display_name":"Safe Reinforcement Learning for Continuous Spaces through Lyapunov-Constrained Behavior","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W4407809681","doi":"https://doi.org/10.3233/978-1-60750-754-3-70"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-60750-754-3-70","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-60750-754-3-70","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","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/A5112945959","display_name":"Fredaric Jack Christon A","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fjerdingen Sigurd A.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5116362527","display_name":"Kyrkjeb oslash Erik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kyrkjebø Erik","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"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":0.51766762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.876800000667572,"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":0.876800000667572,"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/T10320","display_name":"Neural Networks and Applications","score":0.7458000183105469,"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/T10524","display_name":"Traffic control and management","score":0.7360000014305115,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6846197247505188},{"id":"https://openalex.org/keywords/lyapunov-function","display_name":"Lyapunov function","score":0.5625029802322388},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.5009074211120605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4505883753299713},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30827832221984863},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.28525257110595703},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.16636288166046143},{"id":"https://openalex.org/keywords/nonlinear-system","display_name":"Nonlinear system","score":0.08715885877609253},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0782049298286438}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6846197247505188},{"id":"https://openalex.org/C60640748","wikidata":"https://www.wikidata.org/wiki/Q2337858","display_name":"Lyapunov function","level":3,"score":0.5625029802322388},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.5009074211120605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4505883753299713},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30827832221984863},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28525257110595703},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.16636288166046143},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.08715885877609253},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0782049298286438},{"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:10.3233/978-1-60750-754-3-70","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-60750-754-3-70","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856"],"abstract_inverted_index":{"This":[0],"paper":[1,65],"presents":[2],"a":[3,93],"safe":[4,59],"learning":[5,24,44],"strategy":[6],"for":[7,69,106],"continuous":[8,80,87],"state":[9],"and":[10,45,83],"action":[11,71,100],"spaces":[12],"by":[13],"utilizing":[14],"Lyapunov":[15,38],"stability":[16,52],"properties":[17],"of":[18,36,54,76],"the":[19,34,43,51,55,77,86,97,104,111],"studied":[20],"systems.":[21],"The":[22,64],"reinforcement":[23],"algorithm":[25],"Continous":[26],"Actor-Critic":[27],"Learning":[28],"Automation":[29],"(CACLA)":[30],"is":[31,89],"combined":[32],"with":[33],"notion":[35],"control":[37],"functions":[39],"(CLF)":[40],"to":[41,48,57,73,91,96],"limit":[42],"exploration":[46],"behavior":[47],"operate":[49],"inside":[50],"region":[53],"system":[56],"ensure":[58],"operation":[60],"at":[61],"all":[62],"times.":[63],"extends":[66],"previous":[67],"results":[68],"discrete":[70,99],"sets":[72],"take":[74],"advantage":[75],"more":[78],"general":[79],"actions":[81],"sets,":[82],"show":[84],"that":[85],"method":[88],"able":[90],"find":[92],"comparable":[94],"solution":[95],"best":[98],"choices":[101,109],"while":[102],"avoiding":[103],"need":[105],"good":[107],"heuristic":[108],"in":[110],"design":[112],"process.":[113]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}