Approximation of Convex Envelope Using Reinforcement Learning
Systems and Control
2023-11-27 v1 Machine Learning
Systems and Control
Abstract
Oberman gave a stochastic control formulation of the problem of estimating the convex envelope of a non-convex function. Based on this, we develop a reinforcement learning scheme to approximate the convex envelope, using a variant of Q-learning for controlled optimal stopping. It shows very promising results on a standard library of test problems.
Cite
@article{arxiv.2311.14421,
title = {Approximation of Convex Envelope Using Reinforcement Learning},
author = {Vivek S. Borkar and Adit Akarsh},
journal= {arXiv preprint arXiv:2311.14421},
year = {2023}
}