|
gptkbp:instanceOf
|
gptkb:algorithm
|
|
gptkbp:advantage
|
domain independence
anytime property
asymmetrical tree growth
|
|
gptkbp:category
|
gptkb:algorithm
gptkb:search_engine
stochastic algorithm
AI algorithm
|
|
gptkbp:component
|
gptkb:expansion
backpropagation
selection
update
tree search
rollout
random simulation
|
|
gptkbp:fullName
|
gptkb:Monte_Carlo_Tree_Search
|
|
gptkbp:introducedIn
|
2006
|
|
gptkbp:inventedBy
|
gptkb:Rémi_Coulom
|
|
gptkbp:limitation
|
high computational cost
difficulty with sparse rewards
scalability issues in large state spaces
|
|
gptkbp:notableFor
|
gptkb:Go
gptkb:General_Game_Playing
Chess
|
|
gptkbp:relatedTo
|
gptkb:UCT
gptkb:Monte_Carlo_method
gptkb:AlphaGo
gptkb:Minimax
|
|
gptkbp:usedBy
|
gptkb:DeepMind
gptkb:AlphaZero
gptkb:Leela_Zero
|
|
gptkbp:usedIn
|
gptkb:artificial_intelligence
gptkb:reinforcement_learning
planning
game playing
|
|
gptkbp:bfsParent
|
gptkb:UW–Milwaukee_Panther_Arena
gptkb:Milwaukee_County_Transit_System
gptkb:Howard_C._Berkowitz
|
|
gptkbp:bfsLayer
|
7
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
MCTS
|