Q-Learning in Continuous State-Action Space with Noisy and Redundant Inputs by Using a Selective Desensitization Neural Network

Access this Article

Search this Article

Author(s)

Abstract

<p>When applying reinforcement learning (RL) algorithms such as Q-learning to real-world applications, we must consider the influence of sensor noise. The simplest way to reduce such noise influence is to additionally use other types of sensors, but this may require more state space – and probably increase redundancy. Conventional value-function approximators used to RL in continuous state-action space do not deal appropriately with such situations. The selective desensitization neural network (SDNN) has high generalization ability and robustness against noise and redundant input. We therefore propose an SDNN-based value-function approximator for Q-learning in continuous state-action space, and evaluate its performance in terms of robustness against redundant input and sensor noise. Results show that our proposal is strongly robust against noise and redundant input and enables the agent to take better actions by using additional inputs without degrading learning efficiency. These properties are eminently advantageous in real-world applications such as in robotic systems.</p>

Journal

  • Journal of Advanced Computational Intelligence and Intelligent Informatics

    Journal of Advanced Computational Intelligence and Intelligent Informatics 19(6), 825-832, 2015

    Fuji Technology Press Ltd.

Codes

  • NII Article ID (NAID)
    130007673293
  • NII NACSIS-CAT ID (NCID)
    AA12042502
  • Text Lang
    ENG
  • ISSN
    1343-0130
  • NDL Article ID
    026913124
  • NDL Call No.
    Z78-A599
  • Data Source
    NDL  J-STAGE 
Page Top