Encoding human behavior in information design through deep learning
We initiate the study of $\textit {behavioral information design} $ through deep learning. In
information design, a $\textit {sender} $ aims to persuade a $\textit {receiver} $ to take certain …
information design, a $\textit {sender} $ aims to persuade a $\textit {receiver} $ to take certain …
Persuading a learning agent
T Lin, Y Chen - arXiv preprint arXiv:2402.09721, 2024 - arxiv.org
We study a repeated Bayesian persuasion problem (and more generally, any generalized
principal-agent problem with complete information) where the principal does not have …
principal-agent problem with complete information) where the principal does not have …
Computational aspects of Bayesian persuasion under approximate best response
We study Bayesian persuasion under approximate best response, where the receiver may
choose any action that is not too much suboptimal, given their posterior belief upon …
choose any action that is not too much suboptimal, given their posterior belief upon …
Persuading a behavioral agent: Approximately best responding and learning
Y Chen, T Lin - arXiv preprint arXiv:2302.03719, 2023 - arxiv.org
The classic Bayesian persuasion model assumes a Bayesian and best-responding receiver.
We study a relaxation of the Bayesian persuasion model where the receiver can …
We study a relaxation of the Bayesian persuasion model where the receiver can …
Algorithmic Cheap Talk
The literature on strategic communication originated with the influential cheap talk model,
which precedes the Bayesian persuasion model by three decades. This model describes an …
which precedes the Bayesian persuasion model by three decades. This model describes an …
Persuading a Credible Agent
How to optimally persuade an agent who has a private type? When elicitation is feasible,
this amounts to a fairly standard principal-agent-style mechanism design problem, where the …
this amounts to a fairly standard principal-agent-style mechanism design problem, where the …
On the Utility of Accounting for Human Beliefs about AI Behavior in Human-AI Collaboration
To enable effective human-AI collaboration, merely optimizing AI performance while
ignoring humans is not sufficient. Recent research has demonstrated that designing AI …
ignoring humans is not sufficient. Recent research has demonstrated that designing AI …
Leakage-Robust Bayesian Persuasion
We introduce the concept of leakage-robust Bayesian persuasion. Situated between public
persuasion [KG11, CCG23, Xu20] and private persuasion [AB19], leakage-robust …
persuasion [KG11, CCG23, Xu20] and private persuasion [AB19], leakage-robust …
Responding to Promises: No-regret learning against followers with memory
V Hebbar, C Langbort - arXiv preprint arXiv:2410.07457, 2024 - arxiv.org
We consider a repeated Stackelberg game setup where the leader faces a sequence of
followers of unknown types and must learn what commitments to make. While previous …
followers of unknown types and must learn what commitments to make. While previous …
Bias Detection Via Signaling
We introduce and study the problem of detecting whether an agent is updating their prior
beliefs given new evidence in an optimal way that is Bayesian, or whether they are biased …
beliefs given new evidence in an optimal way that is Bayesian, or whether they are biased …