Markov Decision Process (MDP) models are widely used to model decision-making problems in many research fields. MDPs can be readily designed through modeling and simulation(M&S) using the Discrete Event System Specification formalism (DEVS) due to its modular and hierarchical aspects, which improve the explainability of the models. In particular, the separation between the agent and the environment components involved in the traditional reinforcement learning (RL) algorithm, such as Q-Learning, is clearly formalized to enhance observability and envision the integration of AI components in the decision-making process. Our proposed DEVS model also improves the trust of decision makers by mitigating the risk of delegation to machines in decision-making processes. The main focus of this work is to provide the possibility of designing a Markovian system with a modeling and simulation formalism to optimize a decision-making process with greater explainability through simulation. Furthermore, the work involves an investigation based on financial process management, its specification as an MDP-based RL system, and its M&S with DEVS formalism.

"About this title" may belong to another edition of this title.