arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1702.02184cs.LG
收藏

从多线性预测状态表示(PSR)的转换

Transfer from Multiple Linear Predictive State Representations (PSR)

Worcester Polytechnic Institute(伍斯特理工学院)

Sri Ramana Sekharan, Ramkumar Natarajan, Siddharthan Rajasekaran

摘要:

在本文中,我们解决的问题,从多个部分可观察的源环境的政策,部分可观察的目标环境建模为预测状态表示。这是一种全新的方法,除了在完全可观察域中转移的情况之外,没有以前的工作。我们开发的算法,成功地实现政策转移时,我们有模型的源和目标任务,并详细讨论其性能和缺点。这些算法可以作为部分可观测性领域迁移学习的起点。

英文摘要:

In this paper, we tackle the problem of transferring policy from multiple partially observable source environments to a partially observable target environment modeled as predictive state representation. This is an entirely new approach with no previous work, other than the case of transfer in fully observable domains. We develop algorithms to successfully achieve policy transfer when we have the model of both the source and target tasks and discuss in detail their performance and shortcomings. These algorithms could be a starting point for the field of transfer learning in partial observability.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑