Inverse Sequential Hypothesis Testing

Kunal Pattanayak, Vikram Krishnamurthy, Erik Blasch

Abstract: This paper considers a novel formulation of inverse reinforcement learning with behavioral economics constraints to address inverse sequential hypothesis testing (SHT) in Bayesian agents. The aim is to estimate the detection costs by observing the actions of the sequential hypothesis detector. Our methodology involves Bayesian revealed preferences from microeconomics and rational inattention from behavioral economics. First, we show that Bayesian agents optimally performing SHT are rationally inattentive utility maximizers. Using established results in Bayesian revealed preferences, we outline a feasibility test for a data analyst observing the Bayesian agents to estimate their detection costs. Numerical examples illustrate the performance of the inverse sequential hypothesis testing algorithm.