Continuous-time Model-based Reinforcement Learning

Cagatay Yildiz · Markus Heinonen · Harri Lähdesmäki

[ Abstract ] [ Livestream: Visit Reinforcement Learning and Bandits ] [ Paper ]
Wed 21 Jul 7:25 a.m. — 7:30 a.m. PDT

Model-based reinforcement learning (MBRL) approaches rely on discrete-time state transition models whereas physical systems and the vast majority of control tasks operate in continuous-time. To avoid time-discretization approximation of the underlying process, we propose a continuous-time MBRL framework based on a novel actor-critic method. Our approach also infers the unknown state evolution differentials with Bayesian neural ordinary differential equations (ODE) to account for epistemic uncertainty. We implement and test our method on a new ODE-RL suite that explicitly solves continuous-time control systems. Our experiments illustrate that the model is robust against irregular and noisy data, and can solve classic control problems in a sample-efficient manner.

Chat is not available.