How do birds stay warm in winter? Puffing up is just the start. Breakthroughs, discoveries, and DIY tips sent six days a week. Then you notice a robin hopping from branch to branch. Nearby, ducks are calmly swimming in the pond and waddling around on the ice.

We study pure exploration with infinitely many bandit arms generated i.i.d.

In 1weintroduce ourmotivations, ourmain results and discuss the related work.

Wethenshow that under similar assumptions, two closely related problems we callbackdoor filtering and robust generalizationare nearly equivalent.

We attain the optimal eO( T) regret when the dynamics are unknown to the learner, and poly(logT) regret when known, provided that the cost functions are strongly convex (as in LQR).