News for hackers. Stuff that matters.
Re:RL²: Fast Reinforcement Learning via Slow Reinforcement L... by bytefactory on Thursday January 19, 2017 @08:35PM (#13441099)
So...you mean a grad student? ;)
Re:RL²: Fast Reinforcement Learning via Slow Reinforcement L... by Ar-Curunir on Thursday January 19, 2017 @09:25PM (#13441324)
It's called Grad student descent (referring to the grad student's descent into despair :P)