POND: Pessimistic-Optimistic oNline Dispatching

This paper considers constrained online dispatching with unknown arrival, reward and constraint distributions. We propose a novel online dispatching algorithm, named POND, standing for Pessimistic-Optimistic oNline Dispatching, which achieves O(√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.