A Distributional Perspective on Reinforcement Learning

E1878856 UNEXPLORED

"A Distributional Perspective on Reinforcement Learning" is a research work that reframes reinforcement learning by modeling the full distribution of returns instead of just their expected value, laying foundations for distributional RL methods.

Try in SPARQL Jump to: Surface forms Referenced by

All labels observed (1)

Referenced by (1)

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

Will Dabney notableWork A Distributional Perspective on Reinforcement Learning