Persuading a Learning Agent

arXiv:2402.09721v1 Announce Type: cross
Abstract: We study a repeated Bayesian persuasion problem (and more generally, any generalized principal-agent problem with complete information) where the principal does not have commitment power and the agent uses algorithms to learn to respond to the principal's signals. We reduce this problem to a one-shot generalized principal-agent problem with an approximately-best-responding agent. This reduction allows us to show that: if the agent uses contextual no-regret learning algorithms, then the principal can guarantee a utility that …

abstract agent algorithms arxiv bayesian commitment cs.ai cs.gt cs.lg econ.th generalized information learn persuasion power reduce study type