AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Deep Reinforcement Learning and the Alpha Zero Algorithm
Hacker News is notorious for being very like, well, I basically do. This kind of optimization on the low level is not super novel and maybe it's just this particular implementation I compared to was a speed up. It seems like from discussions on Hacker News and so on, the notion of this speeding up the super important algorithm is a bit overblown. But the results itself is totally cool.