Efficient Contextual Bandits with Continuous Actions

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

arxiv: 2006.06040 · v2 · pith:ABBXXWYV · submitted 2020-06-10 · cs.LG · stat.ML

Efficient Contextual Bandits with Continuous Actions

Maryam Majzoubi , Chicheng Zhang , Rajan Chari , Akshay Krishnamurthy , John Langford , Aleksandrs Slivkins This is my paper

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:ABBXXWYV record.json open to challenge →

classification cs.LG stat.ML

keywords actionsalgorithmbanditscontextualcontinuouscomposescomputationallycreate

0 comments

read the original abstract

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

This paper has not been read by Pith yet.

Efficient Contextual Bandits with Continuous Actions

discussion (0)