POND: Pessimistic-Optimistic oNline Dispatch

This paper considers constrained online dispatch with unknown arrival, reward and constraint distributions. We propose a novel online dispatch algorithm, named POND, standing for Pessimistic-Optimistic oNline Dispatch, which achieves $O(\sqrt{T})$ regret and $O(1)$ constraint violation. Both bounds are sharp. Our experiments on synthetic and real datasets show that POND achieves low regret with minimal constraint violations.