Reinforcement learning (RL), is a powerful tool for control
systems engineering, as it allows the agent to learn from
experience and adapt to changing system dynamics.
However, traditional RL methods often require a complete
model of the environment, which can be difficult to obtain
in real-world scenarios and they can be limited by the
accuracy of the environment model. The research aims to
use data-based methods, also known as model free methods
which learn directly from the agent's interactions with the
environment, to achieve greater flexibility and extend the
scope of applications to real-time environments.
Accessibility Controls