Algorithmic Persuasion Through Simulation
This work addresses persuasion in strategic communication for applications like marketing, but it is incremental as it builds on existing Bayesian persuasion frameworks with simulation-based learning.
The paper tackles the problem of a sender persuading a receiver in a Bayesian game with limited information about the receiver's beliefs and utilities, by using an oracle to simulate receiver behavior and designing a polynomial-time querying algorithm to optimize the sender's expected utility.
We study a Bayesian persuasion game where a sender wants to persuade a receiver to take a binary action, such as purchasing a product. The sender is informed about the (real-valued) state of the world, such as the quality of the product, but only has limited information about the receiver's beliefs and utilities. Motivated by customer surveys, user studies, and recent advances in AI, we allow the sender to learn more about the receiver by querying an oracle that simulates the receiver's behavior. After a fixed number of queries, the sender commits to a messaging policy and the receiver takes the action that maximizes her expected utility given the message she receives. We characterize the sender's optimal messaging policy given any distribution over receiver types. We then design a polynomial-time querying algorithm that optimizes the sender's expected utility in this game. We also consider approximate oracles, more general query structures, and costly queries.