Learning How to Strategically Disclose Information
- URL: http://arxiv.org/abs/2403.08741v1
- Date: Wed, 13 Mar 2024 17:44:16 GMT
- Title: Learning How to Strategically Disclose Information
- Authors: Raj Kiriti Velicheti, Melih Bastopcu, S. Rasoul Etesami, Tamer
Ba\c{s}ar
- Abstract summary: We consider an online version of information design where a sender interacts with a receiver of an unknown type.
We show that $mathcalO(sqrtT)$ regret is achievable with full information feedback.
We also propose a novel parametrization that allows the sender to achieve $mathcalO(sqrtT)$ regret for a general convex utility function.
- Score: 6.267574471145217
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Strategic information disclosure, in its simplest form, considers a game
between an information provider (sender) who has access to some private
information that an information receiver is interested in. While the receiver
takes an action that affects the utilities of both players, the sender can
design information (or modify beliefs) of the receiver through signal
commitment, hence posing a Stackelberg game. However, obtaining a Stackelberg
equilibrium for this game traditionally requires the sender to have access to
the receiver's objective. In this work, we consider an online version of
information design where a sender interacts with a receiver of an unknown type
who is adversarially chosen at each round. Restricting attention to Gaussian
prior and quadratic costs for the sender and the receiver, we show that
$\mathcal{O}(\sqrt{T})$ regret is achievable with full information feedback,
where $T$ is the total number of interactions between the sender and the
receiver. Further, we propose a novel parametrization that allows the sender to
achieve $\mathcal{O}(\sqrt{T})$ regret for a general convex utility function.
We then consider the Bayesian Persuasion problem with an additional cost term
in the objective function, which penalizes signaling policies that are more
informative and obtain $\mathcal{O}(\log(T))$ regret. Finally, we establish a
sublinear regret bound for the partial information feedback setting and provide
simulations to support our theoretical results.
Related papers
- Algorithmic Persuasion Through Simulation [51.23082754429737]
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 (binary) state of the world, such as whether the quality of the product is high or low, 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.
arXiv Detail & Related papers (2023-11-29T23:01:33Z) - Information Design in Multi-Agent Reinforcement Learning [61.140924904755266]
Reinforcement learning (RL) is inspired by the way human infants and animals learn from the environment.
Research in computational economics distills two ways to influence others directly: by providing tangible goods (mechanism design) and by providing information (information design)
arXiv Detail & Related papers (2023-05-08T07:52:15Z) - Vulnerabilities of Deep Learning-Driven Semantic Communications to
Backdoor (Trojan) Attacks [70.51799606279883]
This paper highlights vulnerabilities of deep learning-driven semantic communications to backdoor (Trojan) attacks.
Backdoor attack can effectively change the semantic information transferred for poisoned input samples to a target meaning.
Design guidelines are presented to preserve the meaning of transferred information in the presence of backdoor attacks.
arXiv Detail & Related papers (2022-12-21T17:22:27Z) - Sequential Information Design: Learning to Persuade in the Dark [49.437419242582884]
We study a repeated information design problem faced by an informed sender who tries to influence the behavior of a self-interested receiver.
At each round, the sender observes the realizations of random events in the sequential decision making (SDM) problem.
This begets the challenge of how to incrementally disclose such information to the receiver to persuade them to follow (desirable) action recommendations.
arXiv Detail & Related papers (2022-09-08T17:08:12Z) - Multi-Receiver Online Bayesian Persuasion [51.94795123103707]
We study an online learning framework in which the sender repeatedly faces a receiver of an unknown, adversarially selected type.
We focus on the case with no externalities and binary actions, as customary in offline models.
We introduce a general online descent scheme to handle online learning problems with a finite number of possible loss functions.
arXiv Detail & Related papers (2021-06-11T16:05:31Z) - Learning to Persuade on the Fly: Robustness Against Ignorance [26.915262694667746]
We study repeated persuasion between a sender and a stream of receivers where at each time, the sender observes a payoff-relevant state drawn independently and identically from an unknown distribution.
The sender seeks to persuade the receivers into taking actions aligned with the sender's preference by selectively sharing state information.
In contrast to the standard models, neither the sender nor the receivers know the distribution, and the sender has to persuade while learning the distribution on the fly.
arXiv Detail & Related papers (2021-02-19T21:02:15Z) - Signaling in Bayesian Network Congestion Games: the Subtle Power of
Symmetry [66.82463322411614]
The paper focuses on the problem of optimal ex ante persuasive signaling schemes, showing that symmetry is a crucial property for its solution.
We show that an optimal ex ante persuasive scheme can be computed in time when players are symmetric and have affine cost functions.
arXiv Detail & Related papers (2020-02-12T19:38:15Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.