Timezone: »

 
Reinforcement learning in continuous-time and space
Cagatay Yildiz

Sat Jul 23 06:40 AM -- 07:20 AM (PDT) @

In this talk, we will introduce a continuous-time reinforcement learning (CTRL) framework. Our talk starts with a categorization of RL problems and naturally motivates a continuous-time perspective to RL. We then introduce a model-based CTRL approach, which solves physical control tasks using neural ordinary differential equations as a sub-routine. We conclude by briefly introducing recent approaches to CTRL.

Author Information

Cagatay Yildiz (University of Tuebingen)

More from the Same Authors