3.4 RL Agents
This Sections explains the reinforcement learning agent concepts being used throughout this project. First, the Q-Learning approach is introduced, followed by the Deep Q-Learning method. Both methods come with advantages as well as disadvantages and the aim of this section is to provide insight into their limitations with respect to the order placement problem.
[1] https://pdfs.semanticscholar.org/54c4/cf3a8168c1b70f91cf78a3dc98b671935492.pdf