Log In Sign Up

Batched Bandits with Crowd Externalities

by   Romain Laroche, et al.

In Batched Multi-Armed Bandits (BMAB), the policy is not allowed to be updated at each time step. Usually, the setting asserts a maximum number of allowed policy updates and the algorithm schedules them so that to minimize the expected regret. In this paper, we describe a novel setting for BMAB, with the following twist: the timing of the policy update is not controlled by the BMAB algorithm, but instead the amount of data received during each batch, called crowd, is influenced by the past selection of arms. We first design a near-optimal policy with approximate knowledge of the parameters that we prove to have a regret in 𝒪(√(ln x/x)+ϵ) where x is the size of the crowd and ϵ is the parameter error. Next, we implement a UCB-inspired algorithm that guarantees an additional regret in 𝒪(max(Kln T,√(Tln T))), where K is the number of arms and T is the horizon.


page 1

page 2

page 3

page 4


Simple regret for infinitely many armed bandits

We consider a stochastic bandit problem with infinitely many arms. In th...

Reproducible Bandits

In this paper, we introduce the notion of reproducible policies in the c...

Regret Bounds for Thompson Sampling in Restless Bandit Problems

Restless bandit problems are instances of non-stationary multi-armed ban...

Ballooning Multi-Armed Bandits

In this paper, we introduce Ballooning Multi-Armed Bandits (BL-MAB), a n...

Combinatorial Bandits under Strategic Manipulations

We study the problem of combinatorial multi-armed bandits (CMAB) under s...

Near-optimality for infinite-horizon restless bandits with many arms

Restless bandits are an important class of problems with applications in...

Addressing the Long-term Impact of ML Decisions via Policy Regret

Machine Learning (ML) increasingly informs the allocation of opportuniti...