Learning Q-Function Approximations for Hybrid Control Problems.

Sandeep Menta Joseph Warrington John Lygeros Manfred Morari

Published in: IEEE Control. Syst. Lett. (2022)

Keyphrases

control problems
reinforcement learning
learning process
learning algorithm
hybrid learning
active learning
online learning
optimal control
adaptive control
search space
learning tasks
reinforcement learning methods
continuous state spaces