Sequential Information Design: Learning to Persuade in the Dark

09/08/2022
by   Martino Bernasconi, et al.
0

We study a repeated information design problem faced by an informed sender who tries to influence the behavior of a self-interested receiver. We consider settings where the receiver faces a sequential decision making (SDM) problem. At each round, the sender observes the realizations of random events in the SDM problem. This begets the challenge of how to incrementally disclose such information to the receiver to persuade them to follow (desirable) action recommendations. We study the case in which the sender does not know random events probabilities, and, thus, they have to gradually learn them while persuading the receiver. We start by providing a non-trivial polytopal approximation of the set of sender's persuasive information structures. This is crucial to design efficient learning algorithms. Next, we prove a negative result: no learning algorithm can be persuasive. Thus, we relax persuasiveness requirements by focusing on algorithms that guarantee that the receiver's regret in following recommendations grows sub-linearly. In the full-feedback setting – where the sender observes all random events realizations – , we provide an algorithm with Õ(√(T)) regret for both the sender and the receiver. Instead, in the bandit-feedback setting – where the sender only observes the realizations of random events actually occurring in the SDM problem – , we design an algorithm that, given an α∈ [1/2, 1] as input, ensures Õ(T^α) and Õ( T^max{α, 1-α/2}) regrets, for the sender and the receiver respectively. This result is complemented by a lower bound showing that such a regrets trade-off is essentially tight.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/06/2023

Online Mechanism Design for Information Acquisition

We study the problem of designing mechanisms for information acquisition...
research
02/19/2021

Learning to Persuade on the Fly: Robustness Against Ignorance

We study a repeated persuasion setting between a sender and a receiver, ...
research
03/02/2023

Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion

Bayesian persuasion studies how an informed sender should influence beli...
research
06/11/2021

Multi-Receiver Online Bayesian Persuasion

Bayesian persuasion studies how an informed sender should partially disc...
research
11/26/2022

Mediated Cheap Talk Design (with proofs)

We study an information design problem with two informed senders and a r...
research
05/28/2021

Regret-Minimizing Bayesian Persuasion

We study a Bayesian persuasion setting with binary actions (adopt and re...
research
01/31/2023

Selling Information while Being an Interested Party

We study the algorithmic problem faced by an information holder (seller)...

Please sign up or login with your details

Forgot password? Click here to reset