https://users.cg.tuwien.ac.at/zsolnai/wp/wp-content/uploads/2014/04/lightbulb-icon.jpg 256 256 zsolnai https://users.cg.tuwien.ac.at/zsolnai/wp/wp-content/uploads/2018/05/web_logo_2018-03.png zsolnai2015-03-07 21:32:562015-03-08 13:18:22Fun with DeepMind’s Deep Q-learning
Fun with DeepMind’s Deep Q-learning
I have had an awful lot of fun with Google DeepMind’s Deep Q-learning algorithm. It plays Atari Breakout solely based on relying the sensory input, and doesn’t know anything about the game when starting out.
I have also added a patch to fix the visualization when reloading a pre-trained network. The window will appear after the first evaluation batch is done (typically a few minutes). This configuration is able to run Ilya Kuzovkin’s version using less than 1GB VRAM.