Safe Reinforcement Learning Using Black-Box Reachability Analysis

被引：0
|
作者：
Selim, Mahmoud [1 ]
Alanwar, Amr [2 ]
Kousik, Shreyas [3 ]
Gao, Grace [3 ]
Pavone, Marco [3 ]
Johansson, Karl H. [4 ]
机构：
[1] Ain Shams University, Cairo, Egypt
[2] Jacobs University, Bremen, Germany
[3] Stanford University, Stanford,CA, United States
[4] KTH Royal Institute of Technology, Stockholm, Sweden
来源：
arXiv | 2022年
关键词：
Compilation and indexing terms; Copyright 2024 Elsevier Inc;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Learning systems - Motion planning - Multilayer neural networks - Robot programming
引用
收藏
相关论文
共 50 条
  • [1] Safe Reinforcement Learning Using Black-Box Reachability Analysis
    Selim, Mahmoud
    Alanwar, Amr
    Kousik, Shreyas
    Gao, Grace
    Pavone, Marco
    Johansson, Karl H.
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (04) : 10665 - 10672
  • [2] Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning
    Usmanova, Ilnura
    As, Yarden
    Kamgarpour, Maryam
    Krause, Andreas
    JOURNAL OF MACHINE LEARNING RESEARCH, 2024, 25
  • [3] Probabilistic Black-Box Reachability Checking
    Aichernig, Bernhard K.
    Tappler, Martin
    RUNTIME VERIFICATION (RV 2017), 2017, 10548 : 50 - 67
  • [4] Sparse Black-Box Video Attack with Reinforcement Learning
    Xingxing Wei
    Huanqian Yan
    Bo Li
    International Journal of Computer Vision, 2022, 130 : 1459 - 1473
  • [5] Sparse Black-Box Video Attack with Reinforcement Learning
    Wei, Xingxing
    Yan, Huanqian
    Li, Bo
    INTERNATIONAL JOURNAL OF COMPUTER VISION, 2022, 130 (06) : 1459 - 1473
  • [6] Deep Black-Box Reinforcement Learning with Movement Primitives
    Otto, Fabian
    Celik, Onur
    Zhou, Hongyi
    Ziesche, Hanna
    Ngo Anh Vien
    Neumann, Gerhard
    CONFERENCE ON ROBOT LEARNING, VOL 205, 2022, 205 : 1244 - 1265
  • [7] Sablas: Learning Safe Control for Black-Box Dynamical Systems
    Qin, Zengyi
    Sun, Dawei
    Fan, Chuchu
    IEEE ROBOTICS AND AUTOMATION LETTERS, 2022, 7 (02) : 1928 - 1935
  • [8] Deep Reinforcement Learning for Black-box Testing of Android Apps
    Romdhana, Andrea
    Merlo, Alessio
    Ceccato, Mariano
    Tonella, Paolo
    ACM TRANSACTIONS ON SOFTWARE ENGINEERING AND METHODOLOGY, 2022, 31 (04)
  • [9] AutoAttacker: A reinforcement learning approach for black-box adversarial attacks
    Tsingenopoulos, Ilias
    Preuveneers, Davy
    Joosen, Wouter
    2019 4TH IEEE EUROPEAN SYMPOSIUM ON SECURITY AND PRIVACY WORKSHOPS (EUROS&PW), 2019, : 229 - 237
  • [10] Probabilistic black-box reachability checking (extended version)
    Aichernig, Bernhard K.
    Tappler, Martin
    FORMAL METHODS IN SYSTEM DESIGN, 2019, 54 (03) : 416 - 448
12345