Efficient Contextual Bandits with Continuous Actions

06/10/2020

∙

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.

READ FULL TEXT

Efficient Contextual Bandits with Continuous Actions

Efficient Contextual Bandits with Knapsacks via Regression

Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits

Efficient Kernel UCB for Contextual Bandits

Contextual Bandits with Large Action Spaces: Made Practical

Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles

Bandits for Learning to Explain from Explanations

Contextual Bandits with Sparse Data in Web setting

Efficient Contextual Bandits with Continuous Actions

Related Research

Efficient Contextual Bandits with Knapsacks via Regression

Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits

Efficient Kernel UCB for Contextual Bandits

Contextual Bandits with Large Action Spaces: Made Practical

Beyond UCB: Optimal and Efficient Contextual Bandits with Regression Oracles

Bandits for Learning to Explain from Explanations

Contextual Bandits with Sparse Data in Web setting