A PDE-Based Analysis of the Symmetric Two-Armed Bernoulli Bandit

02/11/2022
by   Vladimir A. Kobzar, et al.
0

This work addresses a version of the two-armed Bernoulli bandit problem where the sum of the means of the arms is one (the symmetric two-armed Bernoulli bandit). In a regime where the gap between these means goes to zero and the number of prediction periods approaches infinity, we obtain the leading order terms of the expected regret and pseudoregret for this problem by associating each of them with a solution of a linear parabolic partial differential equation. Our results improve upon the previously known results; specifically we explicitly compute the leading order term of the optimal regret and pseudoregret in three different scaling regimes for the gap. Additionally, we obtain new non-asymptotic bounds for any given time horizon.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/15/2019

Exponential two-armed bandit problem

We consider exponential two-armed bandit problem in which incomes are de...
research
05/05/2016

Copeland Dueling Bandit Problem: Regret Lower Bound, Optimal Algorithm, and Computationally Efficient Algorithm

We study the K-armed dueling bandit problem, a variation of the standard...
research
02/09/2018

Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits

Regret bounds in online learning compare the player's performance to L^*...
research
07/13/2019

A new approach to Poissonian two-armed bandit problem

We consider a continuous time two-armed bandit problem in which incomes ...
research
12/13/2021

Risk and optimal policies in bandit experiments

This paper provides a decision theoretic analysis of bandit experiments....
research
01/25/2019

Gaussian One-Armed Bandit and Optimization of Batch Data Processing

We consider the minimax setup for Gaussian one-armed bandit problem, i.e...
research
05/19/2021

Diffusion Approximations for Thompson Sampling

We study the behavior of Thompson sampling from the perspective of weak ...

Please sign up or login with your details

Forgot password? Click here to reset