Skip to yearly menu bar Skip to main content


Poster

Efficient Contextual Bandits with Continuous Actions

Maryam Majzoubi · Chicheng Zhang · Rajan Chari · Akshay Krishnamurthy · John Langford · Aleksandrs Slivkins

Poster Session 1 #491

Abstract:

We create a computationally tractable learning algorithm for contextual bandits with continuous actions having unknown structure. The new reduction-style algorithm composes with most supervised learning representations. We prove that this algorithm works in a general sense and verify the new functionality with large-scale experiments.

Chat is not available.