English

POND: Pessimistic-Optimistic oNline Dispatching

Machine Learning 2021-05-12 v2 Optimization and Control

Abstract

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)O(\sqrt{T}) regret and O(1)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.

Keywords

Cite

@article{arxiv.2010.09995,
  title  = {POND: Pessimistic-Optimistic oNline Dispatching},
  author = {Xin Liu and Bin Li and Pengyi Shi and Lei Ying},
  journal= {arXiv preprint arXiv:2010.09995},
  year   = {2021}
}
R2 v1 2026-06-23T19:28:30.316Z