DeepAI AI Chat
Log In Sign Up

Thompson Sampling for Gaussian Entropic Risk Bandits

by   Ming Liang Ang, et al.

The multi-armed bandit (MAB) problem is a ubiquitous decision-making problem that exemplifies exploration-exploitation tradeoff. Standard formulations exclude risk in decision making. Risknotably complicates the basic reward-maximising objectives, in part because there is no universally agreed definition of it. In this paper, we consider an entropic risk (ER) measure and explore the performance of a Thompson sampling-based algorithm ERTS under this risk measure by providing regret bounds for ERTS and corresponding instance dependent lower bounds.


page 1

page 2

page 3

page 4


Risk-Constrained Thompson Sampling for CVaR Bandits

The multi-armed bandit (MAB) problem is a ubiquitous decision-making pro...

X-Armed Bandits: Optimizing Quantiles and Other Risks

We propose and analyze StoROO, an algorithm for risk optimization on sto...

A Unifying Theory of Thompson Sampling for Continuous Risk-Averse Bandits

This paper unifies the design and simplifies the analysis of risk-averse...

Robust and Adaptive Planning under Model Uncertainty

Planning under model uncertainty is a fundamental problem across many ap...

Blind Exploration and Exploitation of Stochastic Experts

We present blind exploration and exploitation (BEE) algorithms for ident...

A framework for optimizing COVID-19 testing policy using a Multi Armed Bandit approach

Testing is an important part of tackling the COVID-19 pandemic. Availabi...

Thompson Sampling and Approximate Inference

We study the effects of approximate inference on the performance of Thom...