Regret Analysis of Repeated Delegated Choice

TL;DR

This paper studies a repeated delegated choice problem with online learning, analyzing how a principal can minimize regret when interacting with an agent proposing solutions, considering strategic behavior and utility randomness.

Contribution

It introduces an online learning framework for repeated delegation, analyzing regret bounds under strategic and stochastic utility scenarios, extending prior models.

Findings

Principal can achieve sublinear regret in certain regimes.

Strategic agent behavior affects the learning dynamics.

Regimes identified where delegation procedures succeed or fail.

Abstract

We present a study on a repeated delegated choice problem, which is the first to consider an online learning variant of Kleinberg and Kleinberg, EC'18. In this model, a principal interacts repeatedly with an agent who possesses an exogenous set of solutions to search for efficient ones. Each solution can yield varying utility for both the principal and the agent, and the agent may propose a solution to maximize its own utility in a selfish manner. To mitigate this behavior, the principal announces an eligible set which screens out a certain set of solutions. The principal, however, does not have any information on the distribution of solutions in advance. Therefore, the principal dynamically announces various eligible sets to efficiently learn the distribution. The principal's objective is to minimize cumulative regret compared to the optimal eligible set in hindsight. We explore two dimensions of the problem setup, whether the agent behaves myopically or strategizes across the rounds, and whether the solutions yield deterministic or stochastic utility. Our analysis mainly characterizes some regimes under which the principal can recover the sublinear regret, thereby shedding light on the rise and fall of the repeated delegation procedure in various regimes.