...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>WSEAS Transactions on Signal Processing >Reinforcement Learning in noisy environments: a digital signal processing approach
【24h】

Reinforcement Learning in noisy environments: a digital signal processing approach

机译：嘈杂环境中的强化学习：数字信号处理方法

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Reinforcement Learning (RL) has as its main objective to maximize the rewards of an objective function. This is achieved by an agent which carries out a series of actions to modify the state of the environment. The reinforcements are the cornerstone of the RL. In this work, a modification of the classic scheme of RL is proposed. Our proposal is based on applying a reinforcement with uncertainty; namely, it adds a random signal to the reinforcement. The proposed solution is obtained from the field of Digital Signal Processing. In particular, we propose the use of one of the most simple and widely used filters, such as the Moving Average (MA). The proposed variation is tested in a classical RL problem, namely, Gridworlds with different characteristics regarding size, structure and noise level. Results show that our proposed approach finds the optimal solution under some conditions in which the classical procedure cannot find it. It should also be emphasized that the computational burden of our proposed algorithm is quite lower than that associated with RL classical algorithms, due to the simplicity of the filter.
机译：强化学习（RL）的主要目标是最大化目标功能的回报。这是通过代理执行的，该代理执行一系列操作以修改环境状态。加强件是RL的基石。在这项工作中，提出了对RL经典方案的修改。我们的建议是基于施加不确定性的强化。即，它将随机信号添加到钢筋。所提出的解决方案是从数字信号处理领域获得的。特别是，我们建议使用最简单且使用最广泛的过滤器之一，例如移动平均线（MA）。在经典的RL问题（即在大小，结构和噪声级别方面具有不同特征的Gridworld）中测试了提出的变化。结果表明，我们提出的方法在经典程序无法找到的某些条件下找到了最优解。还应该强调的是，由于滤波器的简单性，我们提出的算法的计算负担远低于与RL经典算法相关的负担。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号