Lenient Regret for Multi-Armed Bandits

08/10/2020
by   Nadav Merlis, et al.
5

We consider the Multi-Armed Bandit (MAB) problem, where the agent sequentially chooses actions and observes rewards for the actions it took. While the majority of algorithms try to minimize the regret. i.e., the cumulative difference between the reward of the best action and the agent's action, this criterion might lead to undesirable results. For example, in large problems, or when the interaction with the environment is brief, finding an optimal arm is infeasible, and regret-minimizing algorithms tend to over-explore. To overcome this issue, algorithms for such settings should instead focus on playing near-optimal arms. To this end, we suggest a new, more lenient, regret criterion that ignores suboptimality gaps smaller than some ϵ. We then present a variant of the Thompson Sampling (TS) algorithm, called ϵ-TS, and prove its asymptotic optimality in terms of the lenient regret. Importantly, we show that when the mean of the optimal arm is high enough, the lenient regret of ϵ-TS is bounded by a constant. Finally, we show that ϵ-TS can be applied to improve the performance when the agent knows a lower bound of the suboptimality gaps.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/24/2022

Risk-averse Contextual Multi-armed Bandit Problem with Linear Payoffs

In this paper we consider the contextual multi-armed bandit problem for ...
research
11/03/2020

Multi-armed Bandits with Cost Subsidy

In this paper, we consider a novel variant of the multi-armed bandit (MA...
research
10/16/2017

On the Hardness of Inventory Management with Censored Demand Data

We consider a repeated newsvendor problem where the inventory manager ha...
research
11/05/2019

Response Prediction for Low-Regret Agents

Companies like Google and Microsoft run billions of auctions every day t...
research
10/23/2020

Finite Continuum-Armed Bandits

We consider a situation where an agent has T ressources to be allocated ...
research
07/10/2018

Bandits with Side Observations: Bounded vs. Logarithmic Regret

We consider the classical stochastic multi-armed bandit but where, from ...
research
03/03/2017

Contextual Multi-armed Bandits under Feature Uncertainty

We study contextual multi-armed bandit problems under linear realizabili...

Please sign up or login with your details

Forgot password? Click here to reset