DeepAI AI Chat
Log In Sign Up

Gamification of Pure Exploration for Linear Bandits

by   Rémy Degenne, et al.

We investigate an active pure-exploration setting, that includes best-arm identification, in the context of linear stochastic bandits. While asymptotically optimal algorithms exist for standard multi-arm bandits, the existence of such algorithms for the best-arm identification in linear bandits has been elusive despite several attempts to address it. First, we provide a thorough comparison and new insight over different notions of optimality in the linear case, including G-optimality, transductive optimality from optimal experimental design and asymptotic optimality. Second, we design the first asymptotically optimal algorithm for fixed-confidence pure exploration in linear bandits. As a consequence, our algorithm naturally bypasses the pitfall caused by a simple but difficult instance, that most prior algorithms had to be engineered to deal with explicitly. Finally, we avoid the need to fully solve an optimal design problem by providing an approach that entails an efficient implementation.


page 1

page 2

page 3

page 4


Choosing Answers in ε-Best-Answer Identification for Linear Bandits

In pure-exploration problems, information is gathered sequentially to an...

Best Arm Identification in Stochastic Bandits: Beyond β-optimality

This paper focuses on best arm identification (BAI) in stochastic multi-...

On the Pareto Frontier of Regret Minimization and Best Arm Identification in Stochastic Bandits

We study the Pareto frontier of two archetypal objectives in stochastic ...

Fully adaptive algorithm for pure exploration in linear bandits

We propose the first fully-adaptive algorithm for pure exploration in li...

Multi-task Representation Learning for Pure Exploration in Linear Bandits

Despite the recent success of representation learning in sequential deci...

Gradient Ascent for Active Exploration in Bandit Problems

We present a new algorithm based on an gradient ascent for a general Act...

High-Dimensional Experimental Design and Kernel Bandits

In recent years methods from optimal linear experimental design have bee...