Improved Regret Bounds for Bandits with Expert Advice

In this research note, we revisit the bandits with expert advice problem. Under a restricted feedback model, we prove a lower bound of order √K T ln(N/K) for the worst-case regret, where K is the number of actions, $N>K$ the number of experts, and T the time horizon. This matches a previously known upper bound of the same order and improves upon the best available lower bound of √K T (ln N) / (ln K). For the standard feedback model, we prove a new instance-based upper bound that depends on the agreement between the experts and provides a logarithmic improvement compared to prior results.