Statements (20)
Predicate | Object |
---|---|
gptkbp:instanceOf |
gptkb:algorithm
Monte Carlo tree search algorithm |
gptkbp:appliesTo |
gptkb:General_Game_Playing
Go AI planning problems |
gptkbp:basedOn |
Upper Confidence Bound (UCB1)
|
gptkbp:citation |
Kocsis, L., & Szepesvári, C. (2006). Bandit based Monte-Carlo Planning. ECML 2006.
|
gptkbp:component |
Monte Carlo Tree Search (MCTS)
|
gptkbp:fullName |
Upper Confidence bounds applied to Trees
|
https://www.w3.org/2000/01/rdf-schema#label |
UCT algorithm
|
gptkbp:introduced |
Csaba Szepesvári
Levente Kocsis |
gptkbp:introducedIn |
2006
|
gptkbp:selectsNodesBy |
balancing exploration and exploitation
|
gptkbp:usedFor |
decision making in large search spaces
|
gptkbp:usedIn |
gptkb:artificial_intelligence
gptkb:reinforcement_learning game playing |
gptkbp:bfsParent |
gptkb:Monte_Carlo_Tree_Search
|
gptkbp:bfsLayer |
6
|