Playing Atari with Deep Reinforcement Learning

The paper presents the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning. The model is a convolutional neural network trained with a variant of Q-learning; its input is raw pixels and its output is a value function estimating future rewards.

Applied to seven Atari 2600 games from the Arcade Learning Environment with no adjustment of the architecture or learning algorithm across games, the method outperforms all previous approaches on six of the games and surpasses a human expert on three of them, demonstrating that a single deep network can learn control directly from pixels.