DeepAI AI Chat
Log In Sign Up

Discontinuity-Sensitive Optimal Control Learning by Mixture of Experts

03/07/2018
by   Gao Tang, et al.
Duke University
0

This paper proposes a discontinuity-sensitive approach to learn the solutions of parametric optimal control problems with high accuracy. Many tasks, ranging from model predictive control to reinforcement learning, may be solved by learning optimal solutions as a function of problem parameters. However, nonconvexity, discrete homotopy classes, and control switching cause discontinuity in the parameter-solution mapping, thus making learning difficult for traditional continuous function approximators. A mixture of experts (MoE) model composed of a classifier and several regressors is proposed to address such an issue. The optimal trajectories of different parameters are clustered such that in each cluster the trajectories are continuous function of problem parameters. Numerical examples on benchmark problems show that training the classifier and regressors individually outperforms joint training of MoE. With suitably chosen clusters, this approach not only achieves lower prediction error with less training data and fewer model parameters, but also leads to dramatic improvements in the reliability of trajectory tracking compared to traditional universal function approximation models (e.g., neural networks).

READ FULL TEXT

page 1

page 5

12/14/2018

Bernstein approximation of optimal control problems

Bernstein polynomial approximation to a continuous function has a slower...
06/12/2019

Reinforcement-Learning-based Adaptive Optimal Control for Arbitrary Reference Tracking

Model-free control based on the idea of Reinforcement Learning is a prom...
01/19/2021

Numerical procedure for optimal control of hybrid systems with sliding modes, Part II

This paper concerns the numerical procedure for solving hybrid optimal c...
07/09/2021

Structured Hammerstein-Wiener Model Learning for Model Predictive Control

This paper aims to improve the reliability of optimal control using mode...
10/21/2020

Markov Data-Based Reference Tracking of Tensegrity Morphing Airfoils

This letter presents a data-based control design for reference tracking ...
09/28/2020

Compositionality of Linearly Solvable Optimal Control in Networked Multi-Agent Systems

In this paper, we discuss the methodology of generalizing the optimal co...