Learning to Plan with Portable Symbols

Learning to Plan with Portable Symbols
复制标题

学习使用便携式符号进行规划

DOI:
--
复制
发表时间:
2018
期刊:
影响因子:
--
通讯作者:
G. Konidaris
G. Konidaris
中科院分区:
--
文献类型:
--
作者:
Steven D. James;Benjamin Rosman;G. Konidaris

文献摘要

参考文献

被引文献

相似文献

我们提出了一个框架,自主学习的便携式符号表示,描述了一个低级别的连续环境的集合。我们表明,抽象表示可以在特定于代理的任务无关空间中学习,当与特定于问题的信息相结合时,可以用于规划。我们演示了在视频游戏领域的知识转移,其中代理学习便携式,任务无关的符号规则,然后学习这些规则的实例化的每一个任务的基础上,减少所需的样本数量来学习一个新的任务的表示。
We present a framework for autonomously learning a portable symbolic representation that describes a collection of low-level continuous environments. We show that abstract representations can be learned in a task-independent space specific to the agent that, when combined with problem-specific information, can be used for planning. We demonstrate knowledge transfer in a video game domain where an agent learns portable, task-independent symbolic rules, and then learns instantiations of these rules on a per-task basis, reducing the number of samples required to learn a representation of a new task.
DOI: --
发表时间: 2017
期刊: Advances in neural information processing systems
影响因子: --
作者:
Andersen,Garrett;Konidaris,George
通讯作者: Konidaris,George