Mnih says the general-purpose DQN learning algorithm could be the first rung on a ladder to artificial intelligence.

Provided with only the same inputs as a human player and no previous real-world knowledge, Google's new deep Q-network (DQN) algorithm uses reinforcement learning to learn new games, and in some ...

DeepMind released a paper in scientific journal Nature this week detailing its deep Q-network (DQN) algorithm's ability to play 49 computer games originally designed for the Atari 2600 - including ...

This OpenAI is a high-quality implementation of the reinforcement learning algorithm (RL algorithm) "OpenAI Baselines"Deep Q-Learning (DQN) and three variations were released.

The DQN algorithm did well on a variety of games, including side-scrolling shooter games, boxing matches and 3D car racing.