Deep reinforcement learning (DQN) is a powerful technique for training artificial intelligence (AI) agents to solve complex tasks. DQN algorithms are based on a type of machine learning called Q-learning, which is a form of reinforcement learning. In DQN, a neural network is used to learn how to associate reward values with different actions, in order to make better choices in future. DQN has been shown to be very effective in training AI agents to play complex games, such as Atari games and Go.