DeepAI AI Chat
Log In Sign Up

Algorithms with Logarithmic or Sublinear Regret for Constrained Contextual Bandits

by   Huasen Wu, et al.
University of California-Davis
University of Illinois at Urbana-Champaign

We study contextual bandits with budget and time constraints, referred to as constrained contextual bandits.The time and budget constraints significantly complicate the exploration and exploitation tradeoff because they introduce complex coupling among contexts over time.Such coupling effects make it difficult to obtain oracle solutions that assume known statistics of bandits. To gain insight, we first study unit-cost systems with known context distribution. When the expected rewards are known, we develop an approximation of the oracle, referred to Adaptive-Linear-Programming (ALP), which achieves near-optimality and only requires the ordering of expected rewards. With these highly desirable features, we then combine ALP with the upper-confidence-bound (UCB) method in the general case where the expected rewards are unknown a priori. We show that the proposed UCB-ALP algorithm achieves logarithmic regret except for certain boundary cases. Further, we design algorithms and obtain similar regret analysis results for more general systems with unknown context distribution and heterogeneous costs. To the best of our knowledge, this is the first work that shows how to achieve logarithmic regret in constrained contextual bandits. Moreover, this work also sheds light on the study of computationally efficient algorithms for general constrained contextual bandits.


page 1

page 2

page 3

page 4


Adapting to Misspecification in Contextual Bandits

A major research direction in contextual bandits is to develop algorithm...

Bypassing the Monster: A Faster and Simpler Optimal Algorithm for Contextual Bandits under Realizability

We consider the general (stochastic) contextual bandit problem under the...

Power-Constrained Bandits

Contextual bandits often provide simple and effective personalization in...

Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits

We study the optimal batch-regret tradeoff for batch linear contextual b...

Delay-Adaptive Learning in Generalized Linear Contextual Bandits

In this paper, we consider online learning in generalized linear context...

On Submodular Contextual Bandits

We consider the problem of contextual bandits where actions are subsets ...

On the Re-Solving Heuristic for (Binary) Contextual Bandits with Knapsacks

In the problem of (binary) contextual bandits with knapsacks (CBwK), the...