Online Allocation and Learning in the Presence of Strategic Agents

TL;DR

This paper develops an online allocation mechanism for sequentially arriving items among strategic agents with unknown valuation distributions, ensuring approximate incentive compatibility and sublinear regret in utility compared to optimal offline policies.

Contribution

It introduces a novel online learning-based allocation mechanism that accounts for strategic behavior and unknown valuation distributions, bridging online auction design and learning.

Findings

Mechanism is approximately Bayesian incentive compatible.

Guarantees sublinear regret for agents' utility.

Works with unknown valuation distributions and strategic agents.

Abstract

We study the problem of allocating $T$ sequentially arriving items among $n$ homogeneous agents under the constraint that each agent must receive a pre-specified fraction of all items, with the objective of maximizing the agents' total valuation of items allocated to them. The agents' valuations for the item in each round are assumed to be i.i.d. but their distribution is a priori unknown to the central planner. Therefore, the central planner needs to implicitly learn these distributions from the observed values in order to pick a good allocation policy. However, an added challenge here is that the agents are strategic with incentives to misreport their valuations in order to receive better allocations. This sets our work apart both from the online auction design settings which typically assume known valuation distributions and/or involve payments, and from the online learning settings that do not consider strategic agents. To that end, our main contribution is an online learning based allocation mechanism that is approximately Bayesian incentive compatible, and when all agents are truthful, guarantees a sublinear regret for individual agents' utility compared to that under the optimal offline allocation policy.