Path Integral Control by Reproducing Kernel Hilbert Space Embedding

Path Integral Control by Reproducing Kernel Hilbert Space Embedding
复制标题

通过再现核希尔伯特空间嵌入进行路径积分控制

DOI:
--
复制
发表时间:
2012
期刊:
ArXiv
影响因子:
--
通讯作者:
S. Vijayakumar
S. Vijayakumar
中科院分区:
--
文献类型:
--
作者:
K. Rawlik;Marc Toussaint;S. Vijayakumar

文献摘要

参考文献

被引文献

相似文献

我们提出了一个嵌入的随机最优控制问题,所谓的路径积分形式,到再生核希尔伯特空间。使用一致的,基于样本的嵌入估计导致一个无模型的,非参数的方法来计算控制问题的近似解。这种提法承认一个分解的问题成一个不变的和任务相关的组件。因此,与该领域中先前的基于样本的方法相比,我们更有效地利用了样本数据,例如,通过允许跨任务重复使用样本。测试问题的数值例子,说明样本效率,提供。
We present an embedding of stochastic optimal control problems, of the so called path integral form, into reproducing kernel Hilbert spaces. Using consistent, sample based estimates of the embedding leads to a model-free, non-parametric approach for calculation of an approximate solution to the control problem. This formulation admits a decomposition of the problem into an invariant and task dependent component. Consequently, we make much more efficient use of the sample data compared to previous sample based approaches in this domain, e.g., by allowing sample re-use across tasks. Numerical examples on test problems, which illustrate the sample efficiency, are provided.
DOI: 10.5555/1756006.1953033
发表时间: 2010-03
期刊: J. Mach. Learn. Res.
影响因子: --
作者:
Evangelos A. Theodorou;J. Buchli;S. Schaal
通讯作者: Evangelos A. Theodorou;J. Buchli;S. Schaal