Reinforcement Learning for Continuous Control: A Quantum Normalized Advantage Function Approach

被引：0
|
作者：
Liu, Yaofu [1 ]
Xu, Chang [1 ]
Jin, Siyuan [2 ]
机构：
[1] Hong Kong Univ Sci & Technol, Dept Phys, Hong Kong, Peoples R China
[2] Hong Kong Univ Sci & Technol, Dept Informat Syst, Hong Kong, Peoples R China
来源：
2023 IEEE INTERNATIONAL CONFERENCE ON QUANTUM SOFTWARE, QSW | 2023年
关键词：
Quantum Computation; Parameterized Quantum Circuit; Reinforcement Learning; Continuous Action Space;
D O I：
10.1109/QSW59989.2023.00020
中图分类号：
TP31 [计算机软件];
学科分类号：
081202 ; 0835 ;
摘要：
In this study, we present a new approach to quantum reinforcement learning that can handle tasks with a range of continuous actions. Our method uses a quantum version of the classic normalized advantage function (QNAF), only needing the Q-value network created by a quantum neural network and avoiding any policy network. We implemented the method by TensorFlow framework. When tested against standard Gym benchmarks, QNAF outperforms classical NAF and prior quantum methods in terms of fewer adjustable parameters. Furthermore, it shows improved stability, reliably converging regardless of changes in initial random parameters.
引用
收藏
页码：83 / 87
页数：5
相关论文
共 50 条
  • [21] Benchmarking Deep Reinforcement Learning for Continuous Control
    Duan, Yan
    Chen, Xi
    Houthooft, Rein
    Schulman, John
    Abbeel, Pieter
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 48, 2016, 48
  • [22] Learning to reach by reinforcement learning using a receptive field based function approximation approach with continuous actions
    Minija Tamosiunaite
    Tamim Asfour
    Florentin Wörgötter
    Biological Cybernetics, 2009, 100 : 249 - 260
  • [23] Learning to reach by reinforcement learning using a receptive field based function approximation approach with continuous actions
    Tamosiunaite, Minija
    Asfour, Tamim
    Woergoetter, Florentin
    BIOLOGICAL CYBERNETICS, 2009, 100 (03) : 249 - 260
  • [24] Reinforcement Learning Approach to Nonequilibrium Quantum Thermodynamics
    Sgroi, Pierpaolo
    Palma, G. Massimo
    Paternostro, Mauro
    PHYSICAL REVIEW LETTERS, 2021, 126 (02)
  • [25] A reinforcement learning approach for quantum state engineering
    Jelena Mackeprang
    Durga B. Rao Dasari
    Jörg Wrachtrup
    Quantum Machine Intelligence, 2020, 2
  • [26] A reinforcement learning approach for quantum state engineering
    Mackeprang, Jelena
    Dasari, Durga B. Rao
    Wrachtrup, Jorg
    QUANTUM MACHINE INTELLIGENCE, 2020, 2 (01)
  • [27] A Reinforcement Learning Approach for Traffic Control
    Baumgart, Urs
    Burger, Michael
    PROCEEDINGS OF THE 7TH INTERNATIONAL CONFERENCE ON VEHICLE TECHNOLOGY AND INTELLIGENT TRANSPORT SYSTEMS (VEHITS), 2021, : 133 - 141
  • [28] Learning Continuous Control Actions for Robotic Grasping with Reinforcement Learning
    Shahid, Asad Ali
    Roveda, Loris
    Piga, Dario
    Braghin, Francesco
    2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2020, : 4066 - 4072
  • [29] Deep reinforcement learning for quantum gate control
    An, Zheng
    Zhou, D. L.
    EPL, 2019, 126 (06)
  • [30] Deep Reinforcement Learning Control of Quantum Cartpoles
    Wang, Zhikang T.
    Ashida, Yuto
    Ueda, Masahito
    PHYSICAL REVIEW LETTERS, 2020, 125 (10)
12345