no code implementations • 9 Jan 2018 • Ben Parr
A simple in-RAM experience replay stores these most recent experiences in a list in RAM, and then copies sampled batches to the GPU for training.
no code implementations • 9 Jan 2018 • Igor Gitman, Deepak Dilipkumar, Ben Parr
The basic idea of both of these algorithms is to make each step of the gradient descent proportional to the current weight norm and independent of the gradient magnitude.
no code implementations • 8 Dec 2017 • Ben Parr, Deepak Dilipkumar, Yu-An Liu
Nintendo's Super Smash Bros. Melee fighting game can be emulated on modern hardware allowing us to inspect internal memory states, such as character positions.