Question d’entretien chez Google DeepMind

Stage 1: An example of an RL algorithm

Réponse à la question d'entretien

Utilisateur anonyme

25 juil. 2020

I described the simplest Monte Carlo RL. Now that I implemented a couple of RL algorithms for my own projects, I don't think I understood the methods that well at the time. It doesn't take much time and definitely pays to try out standard basic algorithms before the interview.