Stochastic Control through Approximate Bayesian Input Inference

by   Joe Watson, et al.

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.


Approximate Inference and Stochastic Optimal Control

We propose a novel reformulation of the stochastic optimal control probl...

Stochastic Optimal Control as Approximate Input Inference

Optimal control of stochastic nonlinear dynamical systems is a major cha...

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

Discrete-time stochastic optimal control remains a challenging problem f...

Active Inference or Control as Inference? A Unifying View

Active inference (AI) is a persuasive theoretical framework from computa...

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

In this study, we adopt age of information as a measure of the staleness...

Control Input Inference of Mobile Agents under Unknown Objective

Trajectory and control secrecy is an important issue in robotics securit...

Bayesian Learning via Neural Schrödinger-Föllmer Flows

In this work we explore a new framework for approximate Bayesian inferen...

Code Repositories


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

view repo

Please sign up or login with your details

Forgot password? Click here to reset