• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Effects of state and action abstraction on development of controllers for concurrent, interfering, non-episodic tasks.
【24h】

Effects of state and action abstraction on development of controllers for concurrent, interfering, non-episodic tasks.

机译：状态和动作抽象对并发，干扰，非突发性任务的控制器开发的影响。

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

The development of controllers for autonomous intelligent agents given a simple task is relatively straightforward and basic techniques can be used to develop such controllers. However, as agents are given more than one task, using basic techniques for developing effective controllers quickly becomes impractical. State and action abstraction are frequently used to counter this explosion of complexity and to make the development of effective controllers for complex problems practical. Unfortunately, most of the work in the literature has focused on complex tasks comprised of sequences of simpler tasks and the more complex tasks comprised of many concurrent, interfering, and non-episodic (CINE) tasks have received little attention. As a result, this dissertation seeks to address this deficiency by providing the first known empirical investigation into the effects of each of these types of abstraction on CINE tasks. The results of this investigation demonstrate that for the single-agent and multi-agent problem domains used, abstraction of the controller's actions provides more benefits in the development and performance of effective controllers than abstraction of the agent's state.;Since there is a lack of work focusing on complex CINE tasks, advances in the implementation and development of controllers capable of addressing such tasks were required. First, we demonstrate that the adaptive fuzzy behavior hierarchy control architecture used in this dissertation has issues when scaled to hierarchies of more than two levels. To address these issues, we introduce a modification to the architecture's implementation that significantly improves the performance of controllers using the same behavior hierarchy. Second, we demonstrate that one of the few known reinforcement learning approaches specifically designed to handle complex CINE tasks is unable to converge to an effective policy for the tasks used here. As a result, we introduce a new reinforcement learning approach that leverages the hierarchical implementation of the controller which is capable of providing statistically significantly better performance in significantly fewer learning experiences. Next, we demonstrate that controllers using adaptive fuzzy behavior hierarchies are able to reuse, without modification, controllers developed for simple tasks in hierarchical controllers developed for a more complex task. Lastly, we demonstrate that since adaptive fuzzy behavior hierarchies effectively use action abstraction, the agent's state can be significantly abstracted in the higher levels of the controller using adaptive priorities which reflect the applicability of lower level behaviors to the agent's current state.
机译：给定简单任务，用于自主智能代理的控制器的开发相对简单，并且可以使用基本技术来开发此类控制器。但是，由于给代理人提供了不止一项任务，因此使用基本技术快速开发有效的控制器变得不切实际。状态和动作抽象经常用于应对这种复杂性的激增，并使针对复杂问题的有效控制器的开发变得切实可行。不幸的是，文献中的大多数工作都集中在由较简单任务序列组成的复杂任务上，而由许多并发，干扰和非周期性（CINE）任务组成的更复杂任务却很少受到关注。结果，本论文试图通过对每种抽象类型对CINE任务的影响进行首次已知的经验研究来解决这一缺陷。这项调查的结果表明，对于所使用的单主体和多主体问题域，控制器行为的抽象化对有效控制器的开发和性能的影响要大于对代理状态的抽象化。致力于复杂的CINE任务的工作，需要在实现和开发能够解决此类任务的控制器方面取得进展。首先，我们证明了本文所采用的自适应模糊行为层次控制体系结构在扩展到两个以上的层次时存在问题。为了解决这些问题，我们对体系结构的实现进行了修改，从而使用相同的行为层次结构显着提高了控制器的性能。其次，我们证明了专门设计用于处理复杂的CINE任务的少数几种已知的强化学习方法之一无法融合到此处所用任务的有效策略。结果，我们引入了一种新的强化学习方法，该方法利用了控制器的分层实现方式，该方法能够在统计上明显减少的学习体验中提供明显更好的性能。接下来，我们证明了使用自适应模糊行为层次结构的控制器能够在不进行修改的情况下重用为简单任务开发的控制器，而在为更复杂的任务开发的层次控制器中，则无需进行修改。最后，我们证明，由于自适应模糊行为层次结构有效地使用了动作抽象，因此可以使用自适应优先级在控制器的较高级别中显着抽象代理的状态，这反映了较低级别行为对代理当前状态的适用性。

著录项

  • 作者

    Eskridge, Brent E.;

  • 作者单位

    The University of Oklahoma.;

  • 授予单位 The University of Oklahoma.;
  • 学科 Computer Science.;Artificial Intelligence.
  • 学位 Ph.D.
  • 年度 2009
  • 页码 178 p.
  • 总页数 178
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

  • 入库时间 2022-08-17 11:38:28

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