Bandits with Partially Observable Offline Data

by   Guy Tennenholtz, et al.

We study linear contextual bandits with access to a large, partially observable, offline dataset that was sampled from some fixed policy. We show that this problem is closely related to a variant of the bandit problem with side information. We construct a linear bandit algorithm that takes advantage of the projected information, and prove regret bounds. Our results demonstrate the ability to take full advantage of partially observable offline data. Particularly, we prove regret bounds that improve current bounds by a factor related to the visible dimensionality of the contexts in the data. Our results indicate that partially observable offline data can significantly improve online learning algorithms. Finally, we demonstrate various characteristics of our approach through synthetic simulations.


page 1

page 2

page 3

page 4


Indexability and Rollout Policy for Multi-State Partially Observable Restless Bandits

Restless multi-armed bandits with partially observable states has applic...

Breaking the √(T) Barrier: Instance-Independent Logarithmic Regret in Stochastic Contextual Linear Bandits

We prove an instance independent (poly) logarithmic regret for stochasti...

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

Regret bounds in online learning compare the player's performance to L^*...

Online Learning via Offline Greedy Algorithms: Applications in Market Design and Optimization

Motivated by online decision-making in time-varying combinatorial enviro...

Offline Behaviors of Online Friends

In this work we analyze traces of mobility and co-location among a group...

Compliance-Aware Bandits

Motivated by clinical trials, we study bandits with observable non-compl...

Improved Algorithms for Bandit with Graph Feedback via Regret Decomposition

The problem of bandit with graph feedback generalizes both the multi-arm...