In these hard times where it is necessary to re-think everyday habits, an ally comes to aid: Machine Learning.
In this talk we'll explore how reinforcement learning (RL) can be used to solve problem of allocating passengers on a bus in an optimal way, taking into consideration social distancing rules.
After briefly explaining what RL is and how it works, we'll start from scratch with Python which will be used to set up the simulation with its own rules; we'll experiment with two approaches using neural networks combined with state-of-the-art RL algorithms, build charts to monitor results.