The complexity of learning linear temporal formulas from examples

被引：0
|
作者：
Fijalkow, Nathanael [1 ,2 ]
Lagarde, Guillaume [1 ]
机构：
[1] Univ Bordeaux, LaBRI, CNRS, Bordeaux, France
[2] Alan Turing Inst, London, England
来源：
INTERNATIONAL CONFERENCE ON GRAMMATICAL INFERENCE, VOL 153 | 2021年 / 153卷
关键词：
passive learning; automata learning; linear temporal logic; approximation algorithms;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
In this paper we initiate the study of the computational complexity of learning linear temporal logic (LTL) formulas from examples. We construct approximation algorithms for fragments of LTL and prove hardness results; in particular we obtain tight bounds for the fragment containing only the next operator and conjunctions, and prove NP-hardness results for many fragments.
引用
收藏
页码：237 / 250
页数：14
相关论文
共 50 条
  • [31] Weight Monitoring with Linear Temporal Logic: Complexity and Decidability
    Baier, Christel
    Klein, Joachim
    Klueppelholz, Sascha
    Wunderlich, Sascha
    PROCEEDINGS OF THE JOINT MEETING OF THE TWENTY-THIRD EACSL ANNUAL CONFERENCE ON COMPUTER SCIENCE LOGIC (CSL) AND THE TWENTY-NINTH ANNUAL ACM/IEEE SYMPOSIUM ON LOGIC IN COMPUTER SCIENCE (LICS), 2014,
  • [32] The complexity of propositional linear temporal logics in simple cases
    Demri, S
    Schnoebelen, P
    STACS 98 - 15TH ANNUAL SYMPOSIUM ON THEORETICAL ASPECTS OF COMPUTER SCIENCE, 1998, 1373 : 61 - 72
  • [33] The complexity of propositional linear temporal logics in simple cases
    Demri, S
    Schnoebelen, P
    INFORMATION AND COMPUTATION, 2002, 174 (01) : 84 - 103
  • [34] Complexity of Safety and coSafety Fragments of Linear Temporal Logic
    Artale, Alessandro
    Geatti, Luca
    Gigante, Nicola
    Mazzullo, Andrea
    Montanari, Angelo
    THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 5, 2023, : 6236 - 6244
  • [35] Individualized Learning Through Non-Linear use of Learning Objects: With Examples From Math and Stat
    Rootzen, Helle
    PROCEEDINGS OF THE 14TH EUROPEAN CONFERENCE ON R-LEARNING (ECEL 2015), 2015, : 500 - 506
  • [36] ON THE DEPTH COMPLEXITY OF FORMULAS
    SHAMIR, E
    SNIR, M
    MATHEMATICAL SYSTEMS THEORY, 1980, 13 (04): : 301 - 322
  • [37] Lifelong reinforcement learning with temporal logic formulas and reward machines
    Zheng, Xuejing
    Yu, Chao
    Zhang, Minjie
    KNOWLEDGE-BASED SYSTEMS, 2022, 257
  • [38] Mapping singly-linked rules to linear temporal logic formulas
    Mackey, Isaac
    Su, Jianwen
    INFORMATION SYSTEMS, 2023, 117
  • [39] Explaining Multi-stage Tasks by Learning Temporal Logic Formulas from Suboptimal Demonstrations
    Chou, Glen
    Ozay, Necmiye
    Berenson, Dmitry
    ROBOTICS: SCIENCE AND SYSTEMS XVI, 2020,
  • [40] Learning from Erroneous Examples
    Tsovaltzi, Dimitra
    McLaren, Bruce M.
    Melis, Erica
    Meyer, Ann-Kristin
    Dietrich, Michael
    Goguadze, George
    INTELLIGENT TUTORING SYSTEMS, PART II, 2010, 6095 : 420 - 422
12345