search

ikostrikov / pytorch-a3c

PyTorch implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".
MIT License
1.23k stars 279 forks source link

Works better with 80x80 images #43

Closed ShaniGam closed 6 years ago

ShaniGam commented 6 years ago

After I ran some experiments I noticed that I got better results when I cancelled the 42x42 resizing. Hope it helps.