Dyna reinforcement learning architecture

E1875540 UNEXPLORED

The Dyna reinforcement learning architecture is a framework introduced by Richard S. Sutton that integrates learning, planning, and acting by using a learned model of the environment to generate simulated experience for updating an agent’s policy.

Try in SPARQL Jump to: Surface forms Referenced by

All labels observed (1)

Label	Occurrences
Dyna reinforcement learning architecture canonical	1

Referenced by (1)

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

Richard S. Sutton → notableWork → Dyna reinforcement learning architecture ⓘ