• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Artificial general intelligence >Learning Problem Solving Skills from Demonstration: An Architectural Approach
【24h】

Learning Problem Solving Skills from Demonstration: An Architectural Approach

机译：通过演示学习解决问题的技能：一种架构方法

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

We present an architectural approach to learning problem solving skills from demonstration, using internal models to represent problem-solving operational knowledge. Internal forward and inverse models are initially learned through active interaction with the environment, and then enhanced and finessed by observing expert teachers. While a single internal model is capable of solving a single goal-oriented task, it is their sequence that enables the system to hierarchically solve more complex task. Activation of models is goal-driven, and internal "mental" simulations are used to predict and anticipate future rewards and perils and to make decisions accordingly. In this approach intelligent system behavior emerges as a coordinated activity of internal models over time governed by sound architectural principles. In this paper we report preliminary results using the game of Sokoban, where the aim is to learn goal-oriented patterns of model activations capable of solving the problem in various contexts.
机译：我们提供了一种体系结构的方法来从演示中学习解决问题的技能，并使用内部模型来表示解决问题的操作知识。内部正向和逆向模型最初是通过与环境的积极互动来学习的，然后通过观察专家教师来增强和完善。尽管单个内部模型能够解决单个面向目标的任务，但正是它们的顺序使系统能够分层解决更复杂的任务。模型的激活是由目标驱动的，内部“心理”模拟用于预测和预期未来的回报和风险，并据此做出决策。在这种方法中，智能系统行为随着内部模型在合理的体系结构原则的控制下随着时间的推移而协调一致地出现。在本文中，我们报告了使用推箱子游戏的初步结果，其目的是学习能够在各种情况下解决问题的模型激活的面向目标的模式。

著录项

  • 来源
    《Artificial general intelligence》|2011年|p.194-203|共10页
  • 会议地点 Mountain View CA(US);Mountain View CA(US)
  • 作者

    Haris Dindo; Antonio Chella; Giuseppe La Tona; Monica Vitali; Eric Nivel; Kristinn R. Thorisson;

  • 作者单位

    Computer Science Engineering, University of Palermo (UNIPA/DINFO) Viale delle Scienze, Ed. 6, 90100 Palermo, Italy;

    Computer Science Engineering, University of Palermo (UNIPA/DINFO) Viale delle Scienze, Ed. 6, 90100 Palermo, Italy;

    Computer Science Engineering, University of Palermo (UNIPA/DINFO) Viale delle Scienze, Ed. 6, 90100 Palermo, Italy;

    Computer Science Engineering, University of Palermo (UNIPA/DINFO) Viale delle Scienze, Ed. 6, 90100 Palermo, Italy;

    Center for Analysis Design of Intelligent Agents and School of Computer Science (CADIA) Reykjavik University, Menntavegur 1, IS-101 Reykjavik, Iceland;

    Center for Analysis Design of Intelligent Agents and School of Computer Science (CADIA) Reykjavik University, Menntavegur 1, IS-101 Reykjavik, Iceland,Icelandic Institute for Intelligent Machines Uranus 2. h., Menntavegur 1, IS-101 Reykjavik, Iceland;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 人工智能理论;
  • 关键词

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