Learning Sampling Distributions for Model Predictive Control Article Swipe

MAKE IMPACT

Jacob Sacks , Byron Boots · YOU? · · 2022 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2212.02587

Sampling-based methods have become a cornerstone of contemporary approaches to Model Predictive Control (MPC), as they make no restrictions on the differentiability of the dynamics or cost function and are straightforward to parallelize. However, their efficacy is highly dependent on the quality of the sampling distribution itself, which is often assumed to be simple, like a Gaussian. This restriction can result in samples which are far from optimal, leading to poor performance. Recent work has explored improving the performance of MPC by sampling in a learned latent space of controls. However, these methods ultimately perform all MPC parameter updates and warm-starting between time steps in the control space. This requires us to rely on a number of heuristics for generating samples and updating the distribution and may lead to sub-optimal performance. Instead, we propose to carry out all operations in the latent space, allowing us to take full advantage of the learned distribution. Specifically, we frame the learning problem as bi-level optimization and show how to train the controller with backpropagation-through-time. By using a normalizing flow parameterization of the distribution, we can leverage its tractable density to avoid requiring differentiability of the dynamics and cost function. Finally, we evaluate the proposed approach on simulated robotics tasks and demonstrate its ability to surpass the performance of prior methods and scale better with a reduced number of samples.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2212.02587

PDF

https://arxiv.org/pdf/2212.02587

OA Status

green

Cited By

2

Related Works

10

OpenAlex ID

https://openalex.org/W4310880059

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4310880059

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2212.02587

Digital Object Identifier

Title

Learning Sampling Distributions for Model Predictive Control

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2022

Year of publication

Publication date

2022-12-05

Full publication date if available

Authors

Jacob Sacks, Byron Boots

List of authors in order

Landing page

https://arxiv.org/abs/2212.02587

Publisher landing page

PDF URL

https://arxiv.org/pdf/2212.02587

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2212.02587

Direct OA link when available

Concepts

Computer science, Heuristics, Model predictive control, Mathematical optimization, Sampling (signal processing), Leverage (statistics), Artificial intelligence, Machine learning, Reinforcement learning, Differentiable function, Importance sampling, Control (management), Mathematics, Statistics, Mathematical analysis, Monte Carlo method, Computer vision, Filter (signal processing)

Top concepts (fields/topics) attached by OpenAlex

Cited by

2

Total citation count in OpenAlex

Citations by year (recent)

2024: 2

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload