Evidence item

DeepMind’s primary DQN paper reports a convolutional Q-learning system trained from raw pixels that outperformed previous reinforcement-learning approaches on six of seven Atari games and exceeded human performance on three. DIRECT_TEXT

Authenticity UNVERIFIED · extraction UNVERIFIED · independence group none (unreviewed) · created seq 15089

Source: Playing Atari with Deep Reinforcement Learning · locator {} · excerpt hash sha256:66dc30bb6a71fe5b2c122f05940abf9b351c128a8d29248436f24933a89ea506

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.