Timezone: »

Efficient Contextual Bandits with Continuous Actions
Maryam Majzoubi · Chicheng Zhang · Rajan Chari · Akshay Krishnamurthy · John Langford · Aleksandrs Slivkins

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #491

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.

Author Information

Maryam Majzoubi (NYU)
Chicheng Zhang (University of Arizona)
Rajan Chari (Microsoft)
Akshay Krishnamurthy (Microsoft)
John Langford (Microsoft Research New York)
Aleksandrs Slivkins (Microsoft Research)

More from the Same Authors