Evidence item

The DQN paper documents a landmark DeepMind deep-reinforcement-learning result, but does not establish that reinforcement learning as a field began there. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 11354

Source: Playing Atari with Deep Reinforcement Learning · locator {} · excerpt hash sha256:63e06e87e7248857212d061186dd66fa34346e9c8e6518b9edc59a056257de32

We present the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. ... We apply our method to seven Atari 2600 games.