Mnih et al. (Nature, 2015) describe an agent they term a deep Q-network that learns policies from high-dimensional sensory inputs by end-to-end reinforcement learning, tested on Atari 2600 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
Human-level control through deep reinforcement learning → states provision → An agent termed a deep Q-network learns policies from high-dimensional sensory inputs by end-to-end reinforcement learning, tested on Atari 2600 games.
Where it appears
No collection page holds this claim. It is listed with its records in the explorer.