works on
optimization 1predictive maintenance 1prognostics 1renewal-reward process 1replacement policies 1series systems 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2025

Convex Is Back: Solving Belief MDPs With Convexity-Informed Deep Reinforcement Learning

Daniel Koutas, Daniel Hettegger, Kostas G. Papakonstantinou +1

We present a novel method for Deep Reinforcement Learning (DRL), incorporating the convex property of the value function over the belief space in Partially Observable Markov Decisi…