
The authors introduce Markov persuasion processes (MPPs) to address sequential scenarios where a sender interacts with myopic receivers in an unknown environment. They propose an algorithm that optimizes regret and violation trade-offs in learning without knowledge of receiver rewards.


coremsg

markov-persuasion-processes-learning-to-persuade-from-scratch


Markov Persuasion Processes: Learning to Persuade from Scratch


title_rewrite


Bayesian persuasion studies strategic information disclosure to influence behavior.
