{"id":"https://openalex.org/W3204172010","doi":"https://doi.org/10.1109/tac.2021.3115080","title":"Probably Approximately Correct Learning in Adversarial Environments With Temporal Logic Specifications","display_name":"Probably Approximately Correct Learning in Adversarial Environments With Temporal Logic Specifications","publication_year":2021,"publication_date":"2021-09-27","ids":{"openalex":"https://openalex.org/W3204172010","doi":"https://doi.org/10.1109/tac.2021.3115080","mag":"3204172010"},"language":"en","primary_location":{"id":"doi:10.1109/tac.2021.3115080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3115080","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-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/A5042986768","display_name":"Min Wen","orcid":"https://orcid.org/0000-0003-1496-8816"},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Min Wen","raw_affiliation_strings":["Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, PA, USA","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068441112","display_name":"Ufuk Topcu","orcid":"https://orcid.org/0000-0003-0819-9985"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ufuk Topcu","raw_affiliation_strings":["Department of Aerospace Engineering and Engineering Mechanics, University of Texas at Austin, Austin, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Aerospace Engineering and Engineering Mechanics, University of Texas at Austin, Austin, TX, USA","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5042986768"],"corresponding_institution_ids":["https://openalex.org/I79576946"],"apc_list":null,"apc_paid":null,"fwci":0.2959,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.62249527,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"67","issue":"10","first_page":"5055","last_page":"5070"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9984999895095825,"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"}},"topics":[{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.9984999895095825,"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/T11178","display_name":"Receptor Mechanisms and Signaling","score":0.9957000017166138,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.994700014591217,"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/notation","display_name":"Notation","score":0.561185896396637},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5219939947128296},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5177521109580994},{"id":"https://openalex.org/keywords/a-priori-and-a-posteriori","display_name":"A priori and a posteriori","score":0.48877736926078796},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.483650803565979},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47102126479148865},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.46245741844177246},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4570408761501312},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.4116727113723755},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3787297010421753},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37380731105804443},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.37064307928085327},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3237146735191345},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.12911710143089294}],"concepts":[{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.561185896396637},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5219939947128296},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5177521109580994},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.48877736926078796},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.483650803565979},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47102126479148865},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.46245741844177246},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4570408761501312},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.4116727113723755},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3787297010421753},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37380731105804443},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.37064307928085327},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3237146735191345},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.12911710143089294},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tac.2021.3115080","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tac.2021.3115080","pdf_url":null,"source":{"id":"https://openalex.org/S184954342","display_name":"IEEE Transactions on Automatic Control","issn_l":"0018-9286","issn":["0018-9286","1558-2523","2334-3303"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Automatic Control","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W6269798","https://openalex.org/W67698512","https://openalex.org/W1496590343","https://openalex.org/W1498432697","https://openalex.org/W1521551618","https://openalex.org/W1556387789","https://openalex.org/W1667094241","https://openalex.org/W1738154394","https://openalex.org/W1964007137","https://openalex.org/W1973039793","https://openalex.org/W2005684815","https://openalex.org/W2074802943","https://openalex.org/W2117927826","https://openalex.org/W2123447947","https://openalex.org/W2161966552","https://openalex.org/W2206317714","https://openalex.org/W2222789563","https://openalex.org/W2293285880","https://openalex.org/W2341066496","https://openalex.org/W2571817908","https://openalex.org/W2792090629","https://openalex.org/W2792346428","https://openalex.org/W2798805125","https://openalex.org/W2895196950","https://openalex.org/W2913325211","https://openalex.org/W2931553127","https://openalex.org/W2963575966","https://openalex.org/W2963604565","https://openalex.org/W2963778636","https://openalex.org/W2986800043","https://openalex.org/W3011250830","https://openalex.org/W3090827750","https://openalex.org/W4231388768","https://openalex.org/W4233413206","https://openalex.org/W4297782545","https://openalex.org/W6668959476","https://openalex.org/W6678481081","https://openalex.org/W6683603353","https://openalex.org/W6731804457"],"related_works":["https://openalex.org/W2891191051","https://openalex.org/W2734912394","https://openalex.org/W2890179775","https://openalex.org/W2022606606","https://openalex.org/W1575028430","https://openalex.org/W2625142831","https://openalex.org/W2902414214","https://openalex.org/W1519821135","https://openalex.org/W118443536","https://openalex.org/W2894720836"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,136,173],"(RL)":[2],"algorithms":[3],"have":[4],"been":[5],"used":[6],"to":[7,10],"learn":[8],"how":[9],"implement":[11],"tasks":[12],"in":[13,30,81,144,174],"uncertain":[14],"and":[15,25,45,72,88,156,180],"partially":[16],"unknown":[17,153,157],"environments.":[18],"In":[19,34],"practice,":[20],"environments":[21],"are":[22,59],"usually":[23],"uncontrolled":[24],"may":[26],"affect":[27],"task":[28,57],"performance":[29],"an":[31,42,145],"adversarial":[32,48],"way.":[33],"this":[35,166],"article,":[36],"we":[37,98],"model":[38],"the":[39,83,117,161,168],"interaction":[40],"between":[41],"RL":[43],"agent":[44],"its":[46],"potentially":[47],"environment":[49],"as":[50,63,74],"a":[51,64,75,94,104,131,141],"turn-based":[52],"zero-sum":[53],"stochastic":[54,175],"game.":[55],"The":[56],"requirements":[58],"represented":[60],"both":[61],"qualitatively":[62],"subset":[65],"of":[66,163],"linear":[67],"temporal":[68],"logic":[69],"(LTL)":[70],"specifications,":[71],"quantitatively":[73],"reward":[76,154],"function.":[77],"For":[78],"each":[79],"case":[80],"which":[82],"LTL":[84],"specification":[85],"is":[86,110,167],"realizable":[87],"can":[89],"be":[90],"equivalently":[91],"transformed":[92],"into":[93],"deterministic":[95],"B\u00fcchi":[96],"automaton,":[97],"show":[99],"that":[100,109,138],"there":[101],"always":[102],"exists":[103],"memoryless":[105],"almost-sure":[106],"winning":[107],"strategy":[108,142],"<inline-formula":[111,124],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[112,125,150],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[113,126],"notation=\"LaTeX\">$\\varepsilon$</tex-math></inline-formula>":[114,127],"-optimal":[115],"for":[116,120],"discounted-sum":[118],"objective":[119],"any":[121],"arbitrary":[122],"positive":[123],".":[128],"We":[129],"propose":[130],"probably":[132],"approximately":[133],"correct":[134],"(PAC)":[135],"algorithm":[137],"learns":[139],"such":[140],"efficiently":[143],"online":[146],"manner":[147],"with":[148,177],"<italic":[149],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">a":[151],"priori</i>":[152],"functions":[155],"transition":[158],"distributions.":[159],"To":[160],"best":[162],"our":[164],"knowledge,":[165],"first":[169],"result":[170],"on":[171],"PAC":[172],"games":[176],"independent":[178],"quantitative":[179],"qualitative":[181],"objectives.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}