TY - GEN
T1 - Learning How to Strategically Disclose Information
AU - Velicheti, Raj Kiriti
AU - Bastopcu, Melih
AU - Etesami, S. Rasoul
AU - Basar, Tamer
N1 - Publisher Copyright:
© 2024 AACC.
PY - 2024
Y1 - 2024
N2 - 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 O(√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 O(√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 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.
AB - 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 O(√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 O(√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 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.
UR - http://www.scopus.com/inward/record.url?scp=85204444063&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85204444063&partnerID=8YFLogxK
U2 - 10.23919/ACC60939.2024.10644843
DO - 10.23919/ACC60939.2024.10644843
M3 - Conference contribution
AN - SCOPUS:85204444063
T3 - Proceedings of the American Control Conference
SP - 1604
EP - 1609
BT - 2024 American Control Conference, ACC 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2024 American Control Conference, ACC 2024
Y2 - 10 July 2024 through 12 July 2024
ER -