• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Symposium on Computer and Information Sciences(ISCIS 2005); 20051026-28; Istanbul(TR) >ARKAQ-Learning: Autonomous State Space Segmentation and Policy Generation
【24h】

ARKAQ-Learning: Autonomous State Space Segmentation and Policy Generation

机译：ARKAQ-Learning：自治状态空间分割和策略生成

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

A real world environment is often partially observable by the agents either because of noisy sensors or incomplete perception. Autonomous strategy planning under uncertainty has two major challenges. First, autonomous segmentation of the state space for a given task; Second, emerging complex behaviors that deal with each state segment. This paper suggests a new approach that handles both by utilizing combination of various techniques, namely ARKAQ-Learning (ART 2-A networks augmented with Kalman Filters and Q-Learning). The algorithm is an online algorithm and it has low space and computational complexity. The algorithm was run for some well known partially observable Markov decision process problems. World Model Generator could reveal the hidden states, mapping non-Markovian model to Markovian internal state space. Policy Generator could build the optimal policy on the internal Markovian state model.
机译：由于噪声传感器或不完整的感知，代理商通常可以部分观察到真实环境。不确定性下的自主策略规划有两个主要挑战。首先，针对给定任务的状态空间的自动分割；其次，出现了涉及每个州段的复杂行为。本文提出了一种新方法，该方法可以通过利用多种技术的组合来处理这两种情况，即ARKAQ-Learning（使用卡尔曼滤波器和Q-Learning增强的ART 2-A网络）。该算法是一种在线算法，具有空间小，计算复杂度高的特点。该算法针对一些众所周知的部分可观察到的马尔可夫决策过程问题运行。世界模型生成器可以揭示隐藏状态，从而将非马尔可夫模型映射到马尔可夫内部状态空间。策略生成器可以在内部马尔可夫状态模型上建立最佳策略。

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