Evidence item

The DQN paper describes a first successful deep-learning model for high-dimensional sensory-input reinforcement learning and reports strong Atari results. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 10541

Source: Playing Atari with Deep Reinforcement Learning · locator {} · excerpt hash sha256:63a33fd920f0c1c2f357c167fa6218e8fccbf5eb0079abc3775b71c49ce4ed9d

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. ... We find that it outperforms all previous approaches on six of the games and surpasses a human expert on three of them.