QR-DQN

E1317485 UNEXPLORED

QR-DQN is a distributional deep reinforcement learning algorithm that models the full return distribution using quantile regression to improve stability and performance over standard DQN.

All labels observed (2)

How this entity was disambiguated

Referenced by (2)

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

Tianshou supportsAlgorithm QR-DQN
Will Dabney notableWork Implicit Quantile Networks for Distributional Reinforcement Learning
linked to: QR-DQN