Neural Optimal Control using Learned System Dynamics
Selim Engin,Volkan Isler,Selim Engin,Volkan Isler
We study the problem of generating control laws for systems with unknown dynamics. Our approach is to represent the controller and the value function with neural networks, and to train them using loss functions adapted from the Hamilton-Jacobi-Bellman (HJB) equations. In the absence of a known dynamics model, our method first learns the state transitions from data collected by interacting with the...
