Skip to yearly menu bar Skip to main content


Combining parametric and nonparametric models for off-policy evaluation

Omer Gottesman · Yao Liu · Scott Sussex · Emma Brunskill · Finale Doshi-Velez

Pacific Ballroom #116

Keywords: [ Theory and Algorithms ]


We consider a model-based approach to perform batch off-policy evaluation in reinforcement learning. Our method takes a mixture-of-experts approach to combine parametric and non-parametric models of the environment such that the final value estimate has the least expected error. We do so by first estimating the local accuracy of each model and then using a planner to select which model to use at every time step as to minimize the return error estimate along entire trajectories. Across a variety of domains, our mixture-based approach outperforms the individual models alone as well as state-of-the-art importance sampling-based estimators.

Live content is unavailable. Log in and register to view live content