DQN (Deep Q-Network)

"Human-Level Control through Deep Reinforcement Learning." First deep learning agent to learn control policies directly from raw pixels via RL. Surpassed human performance on many Atari 2600 games using the same architecture and hyperparameters.

The paper that put DeepMind on the map and catalyzed the deep reinforcement learning field. Introduced experience replay and target networks for stable training. Nature 2015. By Mnih, Kavukcuoglu, Silver et al.