Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ren, Zhaolin, Ren, Tongzheng, Ma, Haitong, Li, Na, Dai, Bo
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909753084477440
author Ren, Zhaolin
Ren, Tongzheng
Ma, Haitong
Li, Na
Dai, Bo
author_facet Ren, Zhaolin
Ren, Tongzheng
Ma, Haitong
Li, Na
Dai, Bo
contents This paper proposes an approach, Spectral Dynamics Embedding Control (SDEC), to optimal control for nonlinear stochastic systems. This method reveals an infinite-dimensional feature representation induced by the system's nonlinear stochastic dynamics, enabling a linear representation of the state-action value function. For practical implementation, this representation is approximated using finite-dimensional truncations, specifically via two prominent kernel approximation methods: random feature truncation and Nystrom approximation. To characterize the effectiveness of these approximations, we provide an in-depth theoretical analysis to characterize the approximation error arising from the finite-dimension truncation and statistical error due to finite-sample approximation in both policy evaluation and policy optimization. Empirically, our algorithm performs favorably against existing stochastic control algorithms on several benchmark problems.
format Preprint
id arxiv_https___arxiv_org_abs_2304_03907
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding
Ren, Zhaolin
Ren, Tongzheng
Ma, Haitong
Li, Na
Dai, Bo
Machine Learning
Optimization and Control
This paper proposes an approach, Spectral Dynamics Embedding Control (SDEC), to optimal control for nonlinear stochastic systems. This method reveals an infinite-dimensional feature representation induced by the system's nonlinear stochastic dynamics, enabling a linear representation of the state-action value function. For practical implementation, this representation is approximated using finite-dimensional truncations, specifically via two prominent kernel approximation methods: random feature truncation and Nystrom approximation. To characterize the effectiveness of these approximations, we provide an in-depth theoretical analysis to characterize the approximation error arising from the finite-dimension truncation and statistical error due to finite-sample approximation in both policy evaluation and policy optimization. Empirically, our algorithm performs favorably against existing stochastic control algorithms on several benchmark problems.
title Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding
topic Machine Learning
Optimization and Control
url https://arxiv.org/abs/2304.03907