Machine learning and artificial intelligence are more than ever changing how we perceive the relationship between humans and technology. In the past few years we witnessed a consistent surge in attention by the STEM community towards this field, which subsequently led to substantial improvements and new walls being broken. As much as learning methods based on large pre-existent datasets are effective, have been proven to be reliable and have been applied in many fields, many researchers’ attention has been leaning towards Reinforcement Learning techniques because of the potential freedom it enables. Reliance on data can be a critical constraint for certain problems.