Lipschitz Continuity in Model-based Reinforcement Learning

We examine the impact of learning Lipschitz continuous models in the context of model-based reinforcement learning. We provide a novel bound on multi-step prediction error of Lipschitz models where we quantify the error using the Wasserstein metric. We go on to prove an error bound for the value-function estimate arising from Lipschitz models and show that the estimated value function is itself Lipschitz. We conclude with empirical results that show the benefits of controlling the Lipschitz constant of neural-network models.

Authors

• Kavosh Asadi
• Dipendra Misra
• Michael L. Littman

Keywords

No keywords are indexed for this paper.