The Efficient Learning of Multiple Task Sequences
The Efficient Learning of Multiple Task Sequences
复制标题
多任务序列的高效学习
DOI：
--
复制
发表时间：
1991
期刊：
影响因子：
--
通讯作者：
Satinder Singh
中科院分区：
文献类型：
--
作者：
Satinder Singh
提出了一种模块化的网络结构和一种基于增量式动态规划的学习算法，它允许单个学习代理学习解决多个马尔可夫决策任务(MDT)，并在任务之间进行大量的学习迁移。我考虑了一类MDT，称为复合任务，它由多个更简单、基本的MDT在时间上串联而成。该体系结构是在一组组合的和基本的MDT上进行培训的。假设复合任务的时间结构是未知的，并且该体系结构学习产生时间分解。结果表明，在一定条件下，复合MDT的解可以通过对其组成的基本MDT的解进行计算廉价的修改来构造。
I present a modular network architecture and a learning algorithm based on incremental dynamic programming that allows a single learning agent to learn to solve multiple Markovian decision tasks (MDTs) with significant transfer of learning across the tasks. I consider a class of MDTs, called composite tasks, formed by temporally concatenating a number of simpler, elemental MDTs. The architecture is trained on a set of composite and elemental MDTs. The temporal structure of a composite task is assumed to be unknown and the architecture learns to produce a temporal decomposition. It is shown that under certain conditions the solution of a composite MDT can be constructed by computationally inexpensive modifications of the solutions of its constituent elemental MDTs.