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.
- Jázmin’s adventures in the supermarket April 12, 2017
- Over Two Million Lectures Given February 14, 2017
- Accelerating Eulerian Fluid Simulation With Convolutional Networks November 29, 2016
- Computational Fluid Dynamics For Simulation of Wind-Terrain Interaction in Flight Simulation June 24, 2016
- Surface-Only Liquids May 19, 2016