In this work, we present a novel paradigm of controlling nonlinear systems via the minimization of the Koopman spectrum cost: a cost over the Koopman operator of the controlled dynamics.
This work studies the problem of sequential control in an unknown, nonlinear dynamical system, where we model the underlying system dynamics as an unknown function in a known Reproducing Kernel Hilbert Space.
We introduce Lyceum, a high-performance computational ecosystem for robot learning.
We study how local trajectory optimization can cope with approximation errors in the value function, and can stabilize and accelerate value function learning.
Reinforcement learning has emerged as a promising methodology for training robot controllers.
This work shows that policies with simple linear and RBF parameterizations can be trained to solve a variety of continuous control tasks, including the OpenAI gym benchmarks.