English

Non-monotonic Resource Utilization in the Bandits with Knapsacks Problem

Machine Learning 2022-09-27 v1 Data Structures and Algorithms Machine Learning

Abstract

Bandits with knapsacks (BwK) is an influential model of sequential decision-making under uncertainty that incorporates resource consumption constraints. In each round, the decision-maker observes an outcome consisting of a reward and a vector of nonnegative resource consumptions, and the budget of each resource is decremented by its consumption. In this paper we introduce a natural generalization of the stochastic BwK problem that allows non-monotonic resource utilization. In each round, the decision-maker observes an outcome consisting of a reward and a vector of resource drifts that can be positive, negative or zero, and the budget of each resource is incremented by its drift. Our main result is a Markov decision process (MDP) policy that has constant regret against a linear programming (LP) relaxation when the decision-maker knows the true outcome distributions. We build upon this to develop a learning algorithm that has logarithmic regret against the same LP relaxation when the decision-maker does not know the true outcome distributions. We also present a reduction from BwK to our model that shows our regret bound matches existing results.

Keywords

Cite

@article{arxiv.2209.12013,
  title  = {Non-monotonic Resource Utilization in the Bandits with Knapsacks Problem},
  author = {Raunak Kumar and Robert Kleinberg},
  journal= {arXiv preprint arXiv:2209.12013},
  year   = {2022}
}

Comments

To appear in the Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS 2022)

R2 v1 2026-06-28T02:01:16.927Z