Grows a search tree unevenly, spending rollouts where the value estimate is most uncertain. Needs a simulator it can query, which is exactly what most real problems lack.
supersedescorrects · extends
classifiesspecializes · part-of
substitutes forapproximates · alternative-to
depends onrequires · validates
Colour is the family; a dashed line is the second member of it.
Drag to pan · scroll to zoom · click a node to open it
This node
requiresdoes not work without Markov Decision Processit searches the tree those transitions define
requiresdoes not work without Upper Confidence Boundevery node of the tree is its own bandit problem
Referenced by
requiresMuZero does not work without thisit plans by searching inside the learned model