Abstract
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.
Original language | English |
---|---|
Title of host publication | Proceedings of the 38th International Conference on Machine Learning, ICML 2021 |
Publisher | JMLR |
Pages | 12009-12018 |
Publication status | Published - 21 Jul 2021 |
MoE publication type | A4 Conference publication |
Event | International Conference on Machine Learning - Virtual, Online Duration: 18 Jul 2021 → 24 Jul 2021 Conference number: 38 |
Publication series
Name | Proceedings of Machine Learning Research |
---|---|
Publisher | PMLR |
Volume | 139 |
ISSN (Electronic) | 2640-3498 |
Conference
Conference | International Conference on Machine Learning |
---|---|
Abbreviated title | ICML |
City | Virtual, Online |
Period | 18/07/2021 → 24/07/2021 |