I read this great article: playing FPS Games with Deep Reinforcement Learning (2017) ( Guillaume Lample, Devendra Singh Chaplot) where they achieve a 4/1 kills/death ratio on Doom against bots.
Assuming we had an unlimited time to train a model and a very powerful machine to use our model in real-time (hello quantum computer), I'd like to know why no one could achieve to build an AI able to play a FPS, using ONLY pixels shown on the screen.ĭisclaimer: I am not tackling this problem and neither am I planning on doing such a thing, this is pure speculation and curiosity.
