5 problems

Order-optimality conjecture. The order optimality of RCA-M should hold when it is used with any index policy that is order optimal for the rested bandit problem.

Let the assumptions of Theorem … should remain true when \bm\mathfrak{R}^N and \overline\mathfrak{R} are replaced by \bm\mathcal{R}^N and \overline\mathcal{R}, respectively…

Let $F$ belong to the function class $\mathcal{C}^{(m)}$. Smooth-noise regret conjecture. Within this function class, a tighter regret lower bound … can be achieved instead of … so…

Let $F$ be the unknown distribution of the market noise in the contextual dynamic pricing problem. Market-noise estimation conjecture. The estimation accuracy of $F$ is crucial for…

Assume that, at each time $t$, Assumption (A4) provides an exact computational oracle for the maximizer ${\hat{\mathbf{x}}}_t$, and that Assumption (A3) imposes concavity of the fu…