Scholarlink

<p>Many real-world control problems inherently have large and continuous&#xa0;domains, leading to the curse of dimensionality in the learning process. This paper proposes a novel critic-only based Neural Reinforcement Learning (NRL) algorithm designed for continuous state spaces. Our approach, called Neural Least Square Policy Iteration (NLSPI), utilizes LSPI method with Radial Basis Function (RBF) network as a function approximator. RBF network offers a continuous and compact representation for continues sensory spaces, enabling the learning system to generalize the learned policy to unseen states. LSPI is employed to adjust the weight parameters of RBF network. Additionally, we present positive theoretical results regarding an error bound between the optimal and the approximated Action Value Function (AVF) for NLSPI. Our proposed method boasts favorable features such as positive mathematical analysis, independence from learning rate, and comparatively good convergence properties. Simulation studies demonstrate the applicability and performance of our learning framework. The overall results indicate that the proposed idea can outperform previously known reinforcement learning algorithms.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A novel neural reinforcement learning algorithm based on critic-only architecture for continuous state control problems

  • 期刊论文

  • 发表日期：

    2025年10月31日

查看全文
  • Omid Mehrabi,
  • Ahmad Fakharian,
  • Mehdi Siahi,
  • Amin Ramezani

摘要

Many real-world control problems inherently have large and continuous domains, leading to the curse of dimensionality in the learning process. This paper proposes a novel critic-only based Neural Reinforcement Learning (NRL) algorithm designed for continuous state spaces. Our approach, called Neural Least Square Policy Iteration (NLSPI), utilizes LSPI method with Radial Basis Function (RBF) network as a function approximator. RBF network offers a continuous and compact representation for continues sensory spaces, enabling the learning system to generalize the learned policy to unseen states. LSPI is employed to adjust the weight parameters of RBF network. Additionally, we present positive theoretical results regarding an error bound between the optimal and the approximated Action Value Function (AVF) for NLSPI. Our proposed method boasts favorable features such as positive mathematical analysis, independence from learning rate, and comparatively good convergence properties. Simulation studies demonstrate the applicability and performance of our learning framework. The overall results indicate that the proposed idea can outperform previously known reinforcement learning algorithms.