4 papers
Branching out: Prognostics-Based Replacement Policies for Series Systems
Daniel Koutas, Daniel Straub
We propose a hybrid planning method for deriving prognostics-based predictive maintenance policies. The method accounts for the available decision options, the information on the f…
Leaf It to Renewal: Improved Predictive Maintenance Policies via Renewal Theory and Decision Trees
Daniel Koutas, Daniel Straub
We propose a hybrid planning method for deriving prognostics-based predictive maintenance policies. The method accounts for the available decision options, the information on the f…
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…
An investigation of belief-free DRL and MCTS for inspection and maintenance planning
Daniel Koutas, Elizabeth Bismut, Daniel Straub
We propose a novel Deep Reinforcement Learning (DRL) architecture for sequential decision processes under uncertainty, as encountered in inspection and maintenance (I&M) planning.…