Timezone: »

Empirical Likelihood for Contextual Bandits
Nikos Karampatziakis · John Langford · Paul Mineiro

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1662

We propose an estimator and confidence interval for computing the value of a policy from off-policy data in the contextual bandit setting. To this end we apply empirical likelihood techniques to formulate our estimator and confidence interval as simple convex optimization problems. Using the lower bound of our confidence interval, we then propose an off-policy policy optimization algorithm that searches for policies with large reward lower bound. We empirically find that both our estimator and confidence interval improve over previous proposals in finite sample regimes. Finally, the policy optimization algorithm we propose outperforms a strong baseline system for learning from off-policy data.

Author Information

Nikos Karampatziakis (Microsoft)
John Langford (Microsoft Research New York)
Paul Mineiro (Microsoft)

More from the Same Authors