Score: 0

Mean-Field Generalisation Bounds for Learning Controls in Stochastic Environments

Published: August 21, 2025 | arXiv ID: 2508.16001v1

By: Boris Baros, Samuel N. Cohen, Christoph Reisinger

Potential Business Impact:

Teaches computers to make smart choices from data.

Business Areas:
Industrial Automation Manufacturing, Science and Engineering

We consider a data-driven formulation of the classical discrete-time stochastic control problem. Our approach exploits the natural structure of many such problems, in which significant portions of the system are uncontrolled. Employing the dynamic programming principle and the mean-field interpretation of single-hidden layer neural networks, we formulate the control problem as a series of infinite-dimensional minimisation problems. When regularised carefully, we provide practically verifiable assumptions for non-asymptotic bounds on the generalisation error achieved by the minimisers to this problem, thus ensuring stability in overparametrised settings, for controls learned using finitely many observations. We explore connections to the traditional noisy stochastic gradient descent algorithm, and subsequently show promising numerical results for some classic control problems.

Country of Origin
🇬🇧 United Kingdom

Page Count
44 pages

Category
Mathematics:
Optimization and Control