C51 distributional DQN

E1878853 UNEXPLORED

C51 distributional DQN is a deep reinforcement learning algorithm that models the full distribution of future returns using a fixed set of value “atoms,” improving stability and performance over standard DQN.

Try in SPARQL Jump to: Surface forms Referenced by

All labels observed (2)

Referenced by (2)

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

Will Dabney knownFor C51 distributional DQN
Will Dabney notableWork Distributional Reinforcement Learning with Quantile Regression
linked to: C51 distributional DQN