An aero-engine life-cycle maintenance policy optimization algorithm: Reinforcement learning approach

Stock Portfolio Optimization Using Water Cycle Algorithm (Comparative Approach)

Portfolio selection process is a subject focused by many researchers. Various criteria involved in this process have undergone alterations over time, necessitating the use of appropriate investment decision support tools. An optimization approach used in different sciences is using meta-heuristic algorithms. In the present study, using Water Cycle Algorithm (WCA), a model was introduced for sel...

A life-cycle system dynamics model of aircraft-engine maintenance

The purpose of this paper is to describe the development and use of a framework for studying the dynamics of the maintenance system of a fleet of military-aircraft engines in a holistic way, as far as both time and place are concerned. The framework is based on a modular system dynamics simulation model of all the inter-related systems, which are involved throughout the life-cycle of the engine...

Algorithm selection of off-policy reinforcement learning algorithm

This paper formalises the problem of online algorithm selection in the context of Reinforcement Learning. The setup is as follows: given an episodic task and a finite number of off-policy RL algorithms, a meta-algorithm has to decide which RL algorithm is in control during the next episode so as to maximize the expected return. The article presents a novel meta-algorithm, called Epochal Stochas...

Future Aero Engine Designs: An Evolving Vision

Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning

Constrained Markov Decision Process (CMDP) is a natural framework for reinforcement learning tasks with safety constraints, where agents learn a policy that maximizes the long-term reward while satisfying the constraints on the long-term cost. A canonical approach for solving CMDPs is the primal-dual method which updates parameters in primal and dual spaces in turn. Existing methods for CMDPs o...