Timezone: »

 
Spotlight
Continuous-time Model-based Reinforcement Learning
Cagatay Yildiz · Markus Heinonen · Harri Lähdesmäki

Wed Jul 21 07:25 AM -- 07:30 AM (PDT) @
in Reinforcement Learning and Bandits »

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.

Keywords: Reinforcement Learning and Planning

Author Information

Cagatay Yildiz (Aalto University)
Markus Heinonen (Aalto University)
Harri Lähdesmäki (Aalto University)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors