News for hackers. Stuff that matters.
Re:Q-Learning by CodiePetersen on Thursday August 15, 2019 @02:23PM (#20708114)
Then multiply that by how many actions you have per state. We'll suppose 9 because you can only change one tile at a time. Then multiply that by 4 bytes assuming we are using a float instead of a double and you get 4.8 gigs of memory for whatever this simple problem is.

There are no comments on this comment yet.