Gaussian Imagination in Bandit Learning

01/06/2022
by   Yueyang Liu, et al.
0

Assuming distributions are Gaussian often facilitates computations that are otherwise intractable. We study the performance of an agent that attains a bounded information ratio with respect to a bandit environment with a Gaussian prior distribution and a Gaussian likelihood function when applied instead to a Bernoulli bandit. Relative to an information-theoretic bound on the Bayesian regret the agent would incur when interacting with the Gaussian bandit, we bound the increase in regret when the agent interacts with the Bernoulli bandit. If the Gaussian prior distribution and likelihood function are sufficiently diffuse, this increase grows at a rate which is at most linear in the square-root of the time horizon, and thus the per-timestep increase vanishes. Our results formalize the folklore that so-called Bayesian agents remain effective when instantiated with diffuse misspecified distributions.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/30/2018

An Information-Theoretic Analysis for Thompson Sampling with Many Actions

Information-theoretic Bayesian regret bounds of Russo and Van Roy captur...
research
05/30/2018

An Information-Theoretic Analysis of Thompson Sampling for Large Action Spaces

Information-theoretic Bayesian regret bounds of Russo and Van Roy captur...
research
02/09/2023

An Information-Theoretic Analysis of Nonstationary Bandit Learning

In nonstationary bandit learning problems, the decision-maker must conti...
research
05/04/2022

Nonstationary Bandit Learning via Predictive Sampling

We propose predictive sampling as an approach to selecting actions that ...
research
05/31/2020

Improved Regret for Zeroth-Order Adversarial Bandit Convex Optimisation

We prove that the information-theoretic upper bound on the minimax regre...
research
02/18/2021

A Bit Better? Quantifying Information for Bandit Learning

The information ratio offers an approach to assessing the efficacy with ...
research
03/02/2022

An Analysis of Ensemble Sampling

Ensemble sampling serves as a practical approximation to Thompson sampli...

Please sign up or login with your details

Forgot password? Click here to reset