Model predictive control with stage cost shaping inspired by reinforcement learning.

Lukas Beckenbach Pavel Osinenko Stefan Streif

Published in: CDC (2019)

Keyphrases

model predictive control
reinforcement learning
reward shaping
control system
predictive control
lowest cost
markov decision processes
function approximation
total cost
state space
optimal policy
reinforcement learning algorithms
neural network
support vector
fuzzy logic
control strategy