.png){kind=icon}
返回
Actor-Critic Learning Control With Regularization and Feature Selection in Policy Gradient Estimation
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2020.2981377.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Actor-critic (AC) learning control architecture has been regarded as an important framework for reinforcement learning (RL) with continuous states and actions. In order to improve learning efficiency and convergence property, previous works have been mainly devoted to solve regularization and feature learning problem in the policy evaluation. In this article, we propose a novel AC learning control method with regularization and feature selection for policy gradient estimation in the actor network. The main contribution is that l(1)-regularization is used on the actor network to achieve the function of feature selection. In each iteration, policy parameters are updated by the regularized dual-averaging (RDA) technique, which solves a minimization problem that involves two terms: one is the running average of the past policy gradients and the other is the l(1)-regularization term of policy parameters. Our algorithm can efficiently calculate the solution of the minimization problem, and we call the new adaptation of policy gradient RDApolicy gradient (RDA-PG). The proposed RDA-PG can learn stochastic and deterministic near-optimal policies. The convergence of the proposed algorithm is established based on the theory of two-timescale stochastic approximation. The simulation and experimental results show that RDA-PG performs feature selection successfully in the actor and learns sparse representations of the actor both in stochastic and deterministic cases. RDA-PG performs better than existing AC algorithms on standard RL benchmark problems with irrelevant features or redundant features.
Keyword:
l(1)-regularization
actor-critic (AC)
policy gradient
regularized dual-averaging (RDA)
reinforcement learning (RL)
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
分享收藏Informing sequential clinical decision-making through reinforcement learning: an empirical study.png)
MACHINE LEARNING
OAAI
MACHINE LEARNINGIF2.9
OAAI分享收藏Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
PREAI
分享收藏
查看更多内容