We organize weekly AI meetings on zoom. We hold these events every Tuesday from 10 am to 11 am unless otherwise noted. We have guests from various universities and industries all over the world. Also, our graduate students present their progress some weeks. If you want to join us in these meetings, please email us at for the zoom info. 

Sep 21, 2021

Çağatay Yıldız from Aalto University, Finland

Continuous-Time Model-Based Reinforcement Learning

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. Such discrete-time approximations typically lead to inaccurate dynamic models, which in turn deteriorate the control learning task. In this talk, I will describe an alternative continuous-time MBRL framework for RL. Our approach infers the unknown state evolution differentials with Bayesian neural ordinary differential equations (ODE) to account for epistemic uncertainty. We also propose a novel continuous-time actor-critic algorithm for policy learning. Our experiments illustrate that the model is robust against irregular and noisy data, is sample-efficient, and can solve control problems which pose challenges to discrete-time MBRL methods.