Necessary and Sufficient Conditions for Inverse Reinforcement Learning of Bayesian Stopping Time Problems
This work addresses the challenge of inferring decision-making strategies in partially observed settings, with applications in domains like online platforms, though it is incremental as it builds on existing IRL and Bayesian frameworks.
The paper tackles the problem of inverse reinforcement learning (IRL) for Bayesian stopping time problems by providing necessary and sufficient conditions to determine if observed actions optimize a cost function, and it demonstrates high accuracy in predicting user engagement on a YouTube dataset with 190000 videos.
This paper presents an inverse reinforcement learning~(IRL) framework for Bayesian stopping time problems. By observing the actions of a Bayesian decision maker, we provide a necessary and sufficient condition to identify if these actions are consistent with optimizing a cost function. In a Bayesian (partially observed) setting, the inverse learner can at best identify optimality wrt the observed strategies. Our IRL algorithm identifies optimality and then constructs set-valued estimates of the cost function.To achieve this IRL objective, we use novel ideas from Bayesian revealed preferences stemming from microeconomics. We illustrate the proposed IRL scheme using two important examples of stopping time problems, namely, sequential hypothesis testing and Bayesian search. As a real-world example, we illustrate using a YouTube dataset comprising metadata from 190000 videos how the proposed IRL method predicts user engagement in online multimedia platforms with high accuracy. Finally, for finite datasets, we propose an IRL detection algorithm and give finite sample bounds on its error probabilities.