Evidence item

DeepMind’s Nature paper documents deep reinforcement learning through a DQN succeeding across 49 Atari games, supporting the claim’s historical RL component. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 13587

Source: Human-level control through deep reinforcement learning · locator {} · excerpt hash sha256:7130ba7ca798d0c2d13b778093ee634061e0c5923d22724a85375270c15c6024

Exact excerpt

Here we use recent advances in training deep neural networks to develop a novel artificial agent, termed a deep Q-network, that can learn successful policies directly from high-dimensional sensory inputs using end-to-end reinforcement learning. ... We demonstrate that the deep Q-network agent, receiving only the pixels and the game score as inputs, was able to surpass the performance of all previous algorithms and achieve a level comparable to that of a professional human games tester across a set of 49 games, using the same algorithm, network architecture and hyperparameters.

Linked claims

Claim	Direction	Relevance	Steps	Counted
f5b7e850	SUPPORT	DIRECT	0	yes

Audits

None.