Autonomous Learning of Action Models for Planning
Autonomous Learning of Action Models for Planning
复制标题
规划行动模型的自主学习
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Alan Fern
中科院分区：
文献类型：
--
作者：
N. Mehta;Prasad Tadepalli;Alan Fern
本文介绍了两个新的框架，学习行动模型的规划。在错误边界规划框架中，学习者可以访问给定模型表示的规划器、模拟器和规划问题生成器，并且旨在学习具有至多多项式数量的错误计划的模型。在有计划的探索框架中，学习者不能使用问题生成器，而是必须设计自己的问题，为它们制定计划，并最多以多项式次数的计划尝试收敛。本文将这些框架中的学习简化为具有片面错误的概念学习，并提供了在这两个框架中成功学习的算法。一个特定的家庭的假设空间被证明是有效的学习在这两个框架。
This paper introduces two new frameworks for learning action models for planning. In the mistake-bounded planning framework, the learner has access to a planner for the given model representation, a simulator, and a planning problem generator, and aims to learn a model with at most a polynomial number of faulty plans. In the planned exploration framework, the learner does not have access to a problem generator and must instead design its own problems, plan for them, and converge with at most a polynomial number of planning attempts. The paper reduces learning in these frameworks to concept learning with one-sided error and provides algorithms for successful learning in both frameworks. A specific family of hypothesis spaces is shown to be efficiently learnable in both the frameworks.