Approximation of Convex Envelope Using Reinforcement Learning

Add code
Nov 24, 2023
Vivek S. Borkar, Adit Akarsh
Figure 1 for Approximation of Convex Envelope Using Reinforcement Learning
Figure 2 for Approximation of Convex Envelope Using Reinforcement Learning
Figure 3 for Approximation of Convex Envelope Using Reinforcement Learning
Figure 4 for Approximation of Convex Envelope Using Reinforcement Learning

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

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.

View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon