Strategic Apple Tasting

by   Keegan Harris, et al.

Algorithmic decision-making in high-stakes domains often involves assigning decisions to agents with incentives to strategically modify their input to the algorithm. In addition to dealing with incentives, in many domains of interest (e.g. lending and hiring) the decision-maker only observes feedback regarding their policy for rounds in which they assign a positive decision to the agent; this type of feedback is often referred to as apple tasting (or one-sided) feedback. We formalize this setting as an online learning problem with apple-tasting feedback where a principal makes decisions about a sequence of T agents, each of which is represented by a context that may be strategically modified. Our goal is to achieve sublinear strategic regret, which compares the performance of the principal to that of the best fixed policy in hindsight, if the agents were truthful when revealing their contexts. Our main result is a learning algorithm which incurs 𝒊Ėƒ(√(T)) strategic regret when the sequence of agents is chosen stochastically. We also give an algorithm capable of handling adversarially-chosen agents, albeit at the cost of 𝒊Ėƒ(T^(d+1)/(d+2)) strategic regret (where d is the dimension of the context). Our algorithms can be easily adapted to the setting where the principal receives bandit feedback – this setting generalizes both the linear contextual bandit problem (by considering agents with incentives) and the strategic classification problem (by allowing for partial feedback).


page 1

page 2

page 3

page 4

∙ 07/26/2023

Online learning in bandits with predicted context

We consider the contextual bandit problem where at each time, the agent ...
∙ 02/14/2023

Effective Dimension in Bandit Problems under Censorship

In this paper, we study both multi-armed and contextual bandit problems ...
∙ 11/14/2018

Incentivizing Exploration with Unbiased Histories

In a social learning setting, there is a set of actions, each of which h...
∙ 08/23/2022

Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instruments

We study offline reinforcement learning under a novel model called strat...
∙ 10/22/2017

Strategic Classification from Revealed Preferences

We study an online linear classification problem, in which the data is g...
∙ 05/03/2020

Autoencoders for strategic decision support

In the majority of executive domains, a notion of normality is involved ...
∙ 06/17/2022

Strategic Representation

Humans have come to rely on machines for reducing excessive information ...

Please sign up or login with your details

Forgot password? Click here to reset