<ul><li>This paper introduces a model-based framework for continuous-time policy evaluation in reinforcement learning, using both Brownian and Lévy noise to model stochastic dynamics affected by rare and extreme events.</li><li>The approach formulates the problem as solving a partial integro-differential equation (PIDE) to compute the value function, with unknown coefficients.</li><li>The challenge is accurately recovering the coefficients, especially for Lévy processes with heavy tail effects, which is addressed using a robust numerical approach combining maximum likelihood estimation and iterative tail correction.</li><li>The method is demonstrated to be effective in recovering heavy-tailed Lévy dynamics and is verified through theoretical error analysis in policy evaluation.</li></ul>

A Robust Model-Based Approach for Continuous-Time Policy Evaluation with Unknown L\'evy Process Dynamics

Discover more