Stochastic Control through Approximate Bayesian Input Inference

05/17/2021
by   Joe Watson, et al.
15

Optimal control under uncertainty is a prevailing challenge in control, due to the difficulty in producing tractable solutions for the stochastic optimization problem. By framing the control problem as one of input estimation, advanced approximate inference techniques can be used to handle the statistical approximations in a principled and practical manner. Analyzing the Gaussian setting, we present a solver capable of several stochastic control methods, and was found to be superior to popular baselines on nonlinear simulated tasks. We draw connections that relate this inference formulation to previous approaches for stochastic optimal control, and outline several advantages that this inference view brings due to its statistical nature.

READ FULL TEXT

Authors

page 1

09/20/2010

Approximate Inference and Stochastic Optimal Control

We propose a novel reformulation of the stochastic optimal control probl...
10/07/2019

Stochastic Optimal Control as Approximate Input Inference

Optimal control of stochastic nonlinear dynamical systems is a major cha...
03/10/2021

Advancing Trajectory Optimization with Approximate Inference: Exploration, Covariance Control and Adaptive Risk

Discrete-time stochastic optimal control remains a challenging problem f...
10/01/2020

Active Inference or Control as Inference? A Unifying View

Active inference (AI) is a persuasive theoretical framework from computa...
10/25/2018

Stochastic Control with Stale Information--Part I: Fully Observable Systems

In this study, we adopt age of information as a measure of the staleness...
05/12/2020

Bayesian optimal control of GHZ states in Rydberg lattices

The ability to prepare non-classical states in a robust manner is essent...
07/08/2020

On Entropic Optimization and Path Integral Control

This article is motivated by the question whether it is possible to solv...

Code Repositories

input-inference-for-control

Input Inference for Control (i2c), a control-as-inference framework for optimal control


view repo
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.