Reinforcement learning of dynamic behavior by using recurrent neural networks

被引：3
|
作者：
Ahmet Onat
Hajime Kita
Yoshikazu Nishikawa
机构：
[1] Graduate School of Kyoto University,Department of Electrical Engineering
[2] Tokyo Institute of Technology,Interdisciplinary Graduate School of Science and Engineering
[3] Osaka Institute of Technology,Faculty of Information Science
来源：
Artificial Life and Robotics | 1997年 / 1卷 / 3期
关键词：
Reinforcement learning; Hidden state; Q-learning; Recurrent neural networks;
D O I：
10.1007/BF02471125
中图分类号：
学科分类号：
摘要：
Reinforcement learning is a learning scheme for finding the optimal policy to control a system, based on a scalar signal representing a reward or a punishment. If the observation of the system by the controller is sufficiently rich to represent the internal state of the system, the controller can achieve the optimal policy simply by learning reactive behavior. However, if the state of the controlled system cannot be assessed completely using current sensory observations, the controller must learn a dynamic behavior to achieve the optimal policy.
引用
收藏
页码：117 / 121
页数：4
相关论文
共 50 条
  • [1] Integrating recurrent neural networks and reinforcement learning for dynamic service composition
    Wang, Hongbing
    Li, Jiajie
    Yu, Qi
    Hong, Tianjing
    Yan, Jia
    Zhao, Wei
    [J]. FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2020, 107 (107): : 551 - 563
  • [2] Stable reinforcement learning with recurrent neural networks
    Knight J.N.
    Anderson C.
    [J]. Journal of Control Theory and Applications, 2011, 9 (3): : 410 - 420
  • [3] Stable reinforcement learning with recurrent neural networks
    James Nate KNIGHT
    Charles ANDERSON
    [J]. Control Theory and Technology, 2011, 9 (03) : 410 - 420
  • [4] Fuzzy inference-based reinforcement learning of dynamic recurrent neural networks
    Jun, HB
    Lee, DW
    Kim, DJ
    Sim, KB
    [J]. SICE '97 - PROCEEDINGS OF THE 36TH SICE ANNUAL CONFERENCE, INTERNATIONAL SESSION PAPERS, 1997, : 1083 - 1088
  • [5] Deep Reinforcement Learning With Bidirectional Recurrent Neural Networks for Dynamic Spectrum Access
    Chen, Peng
    Quo, Shizeng
    Gao, Yulong
    [J]. 2021 IEEE 94TH VEHICULAR TECHNOLOGY CONFERENCE (VTC2021-FALL), 2021,
  • [6] Reinforcement Learning via Recurrent Convolutional Neural Networks
    Shankar, Tanmay
    Dwivedy, Santosha K.
    Guha, Prithwijit
    [J]. 2016 23RD INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2016, : 2592 - 2597
  • [7] A working memory model based on recurrent neural networks using reinforcement learning
    Wang, Mengyuan
    Wang, Yihong
    Xu, Xuying
    Pan, Xiaochuan
    [J]. COGNITIVE NEURODYNAMICS, 2024,
  • [8] Adaptive Drawing Behavior by Visuornotor Learning Using Recurrent Neural Networks
    Sasaki, Kazuma
    Ogata, Tetsuya
    [J]. IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, 2019, 11 (01) : 119 - 128
  • [9] Reinforcement Learning of Linking and Tracing Contours in Recurrent Neural Networks
    Brosch, Tobias
    Neumann, Heiko
    Roelfsema, Pieter R.
    [J]. PLOS COMPUTATIONAL BIOLOGY, 2015, 11 (10)
  • [10] Knowledge-based recurrent neural networks in reinforcement learning
    Le, Tien Dung
    Komeda, Takashi
    Takagi, Motoki
    [J]. PROCEDINGS OF THE 11TH IASTED INTERNATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, 2007, : 169 - 174
12345