According to their paper, DeepMind's Q-learning is indeed passing simplified, vectorized Atari screen pixels straight into a neural net. There's no MPEG or other pre-encoding of the screen, just conversion to grayscale and normalizing to 64x64 pixels.
Slashdot Mirror
According to their paper, DeepMind's Q-learning is indeed passing simplified, vectorized Atari screen pixels straight into a neural net. There's no MPEG or other pre-encoding of the screen, just conversion to grayscale and normalizing to 64x64 pixels.