Timezone: »

Oral
Lipschitz Continuity in Model-based Reinforcement Learning
Kavosh Asadi · Dipendra Misra · Michael L. Littman

Wed Jul 11 02:30 AM -- 02:40 AM (PDT) @ A1

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.