Mnih et al. (arXiv v1, 2013) present a convolutional neural network, trained with a variant of Q-learning on raw pixels, that learns control policies for Atari games.
One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.
What it connects
Playing Atari with Deep Reinforcement Learning → states provision → A convolutional neural network trained with a variant of Q-learning learns control policies from raw pixels.
Where it appears
No collection page holds this claim. It is listed with its records in the explorer.