Searched for: contributor%3A%22Mazo%2C+M.+%28graduation+committee%29%22
(1 - 1 of 1)
document
Dimanidis, Ioannis (author)
We propose a novel method combining elements of supervised- and Q-learning for the control of dynamical systems subject to unknown disturbances. By using the Inverse Optimization framework and in-hindsight information we can derive a causal parametric optimization policy that approximates a non-causal MPC expert. Furthermore, we propose a new...
master thesis 2021