Double DQN

E101969 UNEXPLORED

Double DQN is a reinforcement learning algorithm that improves upon standard Deep Q-Networks by reducing overestimation bias through decoupling action selection from action evaluation.

Jump to: Referenced by

Referenced by (2)

Full triples — surface form annotated when it differs from this entity's canonical label.

OpenAI Baselines → implementsAlgorithm → Double DQN ⓘ

Atari deep Q-network → inspiredAlgorithm → Double DQN ⓘ