Efficient Automatic Tuning for Data-driven Model Predictive Control via Meta-Learning

Baoyu Li, William Edwards, Kris Hauser
3/30/2024
cs.ROcs.LG

No official code found. Best implementation: uiuc-iml/autompc (52 stars, BSD-3-Clause, last commit 2023-06-22).

Abstract

AutoMPC is a Python package that automates and optimizes data-driven model predictive control. However, it can be computationally expensive and unstable when exploring large search spaces using pure Bayesian Optimization (BO). To address these issues, this paper proposes to employ a meta-learning approach called Portfolio that improves AutoMPC's efficiency and stability by warmstarting BO. Portfolio optimizes initial designs for BO using a diverse set of configurations from previous tasks and stabilizes the tuning process by fixing initial configurations instead of selecting them randomly. Experimental results demonstrate that Portfolio outperforms the pure BO in finding desirable solutions for AutoMPC within limited computational resources on 11 nonlinear control simulation benchmarks and 1 physical underwater soft robot dataset.

View on arXivView PDF

Code Implementations(1)

uiuc-iml/autompcCommunity100%
BSD-3-Clause

Automatic Tuning for Data-driven Model Predictive Control

5210PythonFeb 16, 20233 years agoBSD-3-Clause

Similar Papers

Stability-informed Bayesian Optimization for MPC Cost Function Learning

83% match2024

Towards an Adaptable and Generalizable Optimization Engine in Decision and Control: A Meta Reinforcement Learning Approach

82% match2024

A Safe Reinforcement Learning driven Weights-varying Model Predictive Control for Autonomous Vehicle Motion Control

82% match2024

MALIBO: Meta-learning for Likelihood-free Bayesian Optimization

80% match1 repo22023

Deep Model Predictive Optimization

80% match2 repos1.4k2023

An Automatic Tuning MPC with Application to Ecological Cruise Control

80% match2023

Cite this paper

@article{li2024efficient,
  title  = {Efficient Automatic Tuning for Data-driven Model Predictive Control via Meta-Learning},
  author = {Baoyu Li and William Edwards and Kris Hauser},
  year   = {2024},
  eprint = {2404.00232},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2404.00232v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2404.00232.svg)](https://codeofpaper.com/paper/2404.00232)

Discussion