dorsal/arxiv
View SchemaA linear theory for control of non-linear stochastic systems
| Authors | H. J. Kappen |
|---|---|
| Categories | |
| ArXiv ID | physics/0411119 |
| URL | https://arxiv.org/abs/physics/0411119 |
| DOI | 10.1103/PhysRevLett.95.200201 |
Abstract
We address the role of noise and the issue of efficient computation in stochastic optimal control problems. We consider a class of non-linear control problems that can be formulated as a path integral and where the noise plays the role of temperature. The path integral displays symmetry breaking and there exist a critical noise value that separates regimes where optimal control yields qualitatively different solutions. The path integral can be computed efficiently by Monte Carlo integration or by Laplace approximation, and can therefore be used to solve high dimensional stochastic control problems.
{
"annotation_id": "08fb9bc9-d612-4ffc-a89e-8b1fcbd3b1a6",
"date_created": "2026-03-02T18:00:53.851000Z",
"date_modified": "2026-03-02T18:00:53.851000Z",
"file_hash": "e4fea6fadcb009040a26e5c19bb02eb166a92a6150892ebd6ff4c17b7fad1ed4",
"private": false,
"record": {
"abstract": "We address the role of noise and the issue of efficient computation in\nstochastic optimal control problems. We consider a class of non-linear control\nproblems that can be formulated as a path integral and where the noise plays\nthe role of temperature. The path integral displays symmetry breaking and there\nexist a critical noise value that separates regimes where optimal control\nyields qualitatively different solutions. The path integral can be computed\nefficiently by Monte Carlo integration or by Laplace approximation, and can\ntherefore be used to solve high dimensional stochastic control problems.",
"arxiv_id": "physics/0411119",
"authors": [
"H. J. Kappen"
],
"categories": [
"physics.comp-ph",
"physics.gen-ph"
],
"doi": "10.1103/PhysRevLett.95.200201",
"title": "A linear theory for control of non-linear stochastic systems",
"url": "https://arxiv.org/abs/physics/0411119"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "b65574ce-f0d3-43e6-a190-6275e4b78540",
"id": "arXiv Dataset IDs",
"type": "Model",
"variant": "snapshot-2026-03-01",
"version": "0.1.0"
},
"user_id": 1000002
}