Convergence of Bayesian Control Rule

02/16/2010
by   Pedro A. Ortega, et al.
0

Recently, new approaches to adaptive control have sought to reformulate the problem as a minimization of a relative entropy criterion to obtain tractable solutions. In particular, it has been shown that minimizing the expected deviation from the causal input-output dependencies of the true plant leads to a new promising stochastic control rule called the Bayesian control rule. This work proves the convergence of the Bayesian control rule under two sufficient assumptions: boundedness, which is an ergodicity condition; and consistency, which is an instantiation of the sure-thing principle.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/07/2010

A Minimum Relative Entropy Controller for Undiscounted Markov Decision Processes

Adaptive control problems are notoriously difficult to solve even in the...
research
11/26/2009

A Bayesian Rule for Adaptive Control based on Causal Interventions

Explaining adaptive behavior is a central problem in artificial intellig...
research
03/21/2020

Learning in Networked Control Systems

We design adaptive controller (learning rule) for a networked control sy...
research
08/11/2021

Uniform Complete Observability of Mass and Rotational Inertial Parameters in Adaptive Identification of Rigid-Body Plant Dynamics

This paper addresses the long-standing open problem of observability of ...
research
09/01/2017

Convergence Analysis of Deterministic Kernel-Based Quadrature Rules in Misspecified Settings

This paper presents convergence analysis of kernel-based quadrature rule...
research
12/03/2020

VICToRy: Visual Interactive Consistency Management in Tolerant Rule-based Systems

In the field of Model-Driven Engineering, there exist numerous tools tha...

Please sign up or login with your details

Forgot password? Click here to reset