{"id":"https://openalex.org/W3090425956","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207384","title":"Safe Reinforcement Learning via Probabilistic Timed Computation Tree Logic","display_name":"Safe Reinforcement Learning via Probabilistic Timed Computation Tree Logic","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3090425956","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207384","mag":"3090425956"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/A5101627965","display_name":"Qian Li","orcid":"https://orcid.org/0000-0001-8270-2425"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Li Qian","raw_affiliation_strings":["East China Normal University, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100725604","display_name":"Jing Liu","orcid":"https://orcid.org/0000-0003-3600-4647"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Liu","raw_affiliation_strings":["East China Normal University, China"],"affiliations":[{"raw_affiliation_string":"East China Normal University, China","institution_ids":["https://openalex.org/I66867065"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101627965"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":0.3977,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.69057135,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9979000091552734,"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":0.9979000091552734,"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/T10142","display_name":"Formal Methods in Verification","score":0.9977999925613403,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.9887999892234802,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/supervisor","display_name":"Supervisor","score":0.8775094747543335},{"id":"https://openalex.org/keywords/probabilistic-ctl","display_name":"Probabilistic CTL","score":0.815421462059021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7749264240264893},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7484496235847473},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.7319018244743347},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5641793608665466},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5412160754203796},{"id":"https://openalex.org/keywords/supervisory-control","display_name":"Supervisory control","score":0.4482446610927582},{"id":"https://openalex.org/keywords/computation-tree-logic","display_name":"Computation tree logic","score":0.4450560510158539},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3814258873462677},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.36537373065948486},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3224738836288452},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.2804908752441406},{"id":"https://openalex.org/keywords/temporal-logic","display_name":"Temporal logic","score":0.24681761860847473},{"id":"https://openalex.org/keywords/probabilistic-analysis-of-algorithms","display_name":"Probabilistic analysis of algorithms","score":0.1398947536945343},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10728657245635986}],"concepts":[{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.8775094747543335},{"id":"https://openalex.org/C52063229","wikidata":"https://www.wikidata.org/wiki/Q7246845","display_name":"Probabilistic CTL","level":4,"score":0.815421462059021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7749264240264893},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7484496235847473},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.7319018244743347},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5641793608665466},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5412160754203796},{"id":"https://openalex.org/C92991967","wikidata":"https://www.wikidata.org/wiki/Q7644329","display_name":"Supervisory control","level":3,"score":0.4482446610927582},{"id":"https://openalex.org/C198008173","wikidata":"https://www.wikidata.org/wiki/Q1040040","display_name":"Computation tree logic","level":3,"score":0.4450560510158539},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3814258873462677},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.36537373065948486},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3224738836288452},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2804908752441406},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.24681761860847473},{"id":"https://openalex.org/C24404364","wikidata":"https://www.wikidata.org/wiki/Q7246846","display_name":"Probabilistic analysis of algorithms","level":3,"score":0.1398947536945343},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10728657245635986},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207384","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207384","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W32403112","https://openalex.org/W134786152","https://openalex.org/W1601373402","https://openalex.org/W1845972764","https://openalex.org/W1996625075","https://openalex.org/W2048355938","https://openalex.org/W2107726111","https://openalex.org/W2120158398","https://openalex.org/W2121863487","https://openalex.org/W2133632477","https://openalex.org/W2134991157","https://openalex.org/W2155968351","https://openalex.org/W2169619645","https://openalex.org/W2235028240","https://openalex.org/W2288565641","https://openalex.org/W2744647809","https://openalex.org/W2746553466","https://openalex.org/W2787908307","https://openalex.org/W2952245079","https://openalex.org/W2952720101","https://openalex.org/W2963530628","https://openalex.org/W2963575966","https://openalex.org/W2964616600","https://openalex.org/W2966537673","https://openalex.org/W4214717370","https://openalex.org/W4242441073","https://openalex.org/W4294399973","https://openalex.org/W4297780563","https://openalex.org/W6677916085","https://openalex.org/W6682367392","https://openalex.org/W6685043521","https://openalex.org/W6689917546","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W1536962364","https://openalex.org/W46796605","https://openalex.org/W2333630979","https://openalex.org/W1502177156","https://openalex.org/W2325169597","https://openalex.org/W4309988904","https://openalex.org/W2331919730","https://openalex.org/W4317418604","https://openalex.org/W2070318121","https://openalex.org/W2142570643"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"aims":[2],"to":[3,27,31,43,90],"discover":[4],"an":[5],"optimal":[6],"policy":[7],"that":[8],"maximizes":[9],"reward":[10],"based":[11],"on":[12],"the":[13,17,32,39,45,65,68,72,75,79,82,88,92,104,108],"feedback":[14],"signal.":[15],"Although":[16],"method":[18,119],"succeeds":[19],"in":[20],"numerous":[21],"systems,":[22],"it":[23],"may":[24],"not":[25],"apply":[26],"safe-critical":[28],"systems":[29],"due":[30],"absence":[33],"of":[34,81,110,122],"safety":[35],"protection":[36],"mechanism.":[37],"Besides,":[38],"agent":[40,83],"is":[41,70],"unable":[42],"model":[44,69],"environment":[46],"accurately":[47],"if":[48],"getting":[49],"biased":[50],"observation.":[51],"We":[52,116],"present":[53],"a":[54,112],"safe":[55],"algorithm":[56],"called":[57],"Safe":[58],"Control":[59],"with":[60],"Supervisor":[61],"(SCS)":[62],"for":[63],"addressing":[64],"limitation.":[66],"If":[67,102],"accurate,":[71],"supervisor":[73,105],"monitors":[74],"system":[76,89],"and":[77],"repairs":[78],"action":[80],"at":[84],"runtime,":[85],"which":[86],"guides":[87],"obey":[91],"specification":[93],"described":[94],"by":[95],"probabilistic":[96],"timed":[97],"Computation":[98],"Tree":[99],"Logic":[100],"(ptCTL).":[101],"not,":[103],"would":[106],"maximize":[107],"probability":[109],"satisfying":[111],"given":[113],"task":[114],"specification.":[115],"validate":[117],"our":[118],"through":[120],"experiments":[121],"adaptive":[123],"cruise":[124],"control":[125],"under":[126],"uncertainty.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}