When are Kalman-filter restless bandits indexable?

09/15/2015

∙

We study the restless bandit associated with an extremely simple scalar Kalman filter model in discrete time. Under certain assumptions, we prove that the problem is indexable in the sense that the Whittle index is a non-decreasing function of the relevant belief state. In spite of the long history of this problem, this appears to be the first such proof. We use results about Schur-convexity and mechanical words, which are particular binary strings intimately related to palindromes.

READ FULL TEXT

When are Kalman-filter restless bandits indexable?

An Explicit Probabilistic Derivation of Inflation in a Scalar Ensemble Kalman Filter for Finite Step, Finite Ensemble Convergence

Kalman Filter from the Mutual Information Perspective

Stochastic Formulation of Causal Digital Twin: Kalman Filter Algorithm

Unscented Kalman filter with stable embedding for simple, accurate and computationally efficient state estimation of systems on manifolds in Euclidean space

Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter

UltimateKalman: Flexible Kalman Filtering and Smoothing Using Orthogonal Transformations

Intuitive Neuromyoelectric Control of a Dexterous Bionic Arm Using a Modified Kalman Filter

When are Kalman-filter restless bandits indexable?

Related Research

An Explicit Probabilistic Derivation of Inflation in a Scalar Ensemble Kalman Filter for Finite Step, Finite Ensemble Convergence

Kalman Filter from the Mutual Information Perspective

Stochastic Formulation of Causal Digital Twin: Kalman Filter Algorithm

Unscented Kalman filter with stable embedding for simple, accurate and computationally efficient state estimation of systems on manifolds in Euclidean space

Design of experiments for the calibration of history-dependent models via deep reinforcement learning and an enhanced Kalman filter

UltimateKalman: Flexible Kalman Filtering and Smoothing Using Orthogonal Transformations

Intuitive Neuromyoelectric Control of a Dexterous Bionic Arm Using a Modified Kalman Filter