Path Integral Control by Reproducing Kernel Hilbert Space Embedding

Abstract

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.

References in corpus (3)

• A linear theory for control of non-linear stochastic systems
• Kernel Belief Propagation
• Modelling transition dynamics in MDPs with RKHS embeddings

Cited by in corpus (5)

• Real-Time Stochastic Optimal Control for Multi-agent Quadrotor Systems
• Sample Efficient Path Integral Control under Uncertainty
• Characteristic Kernels and Infinitely Divisible Distributions
• Model-based Kernel Sum Rule: Kernel Bayesian Inference with Probabilistic Models
• Nonparametric Infinite Horizon Kullback-Leibler Stochastic Control