Paper ID: 2311.14421

Approximation of Convex Envelope Using Reinforcement Learning

Vivek S. Borkar, Adit Akarsh

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.

Submitted: Nov 24, 2023