|
gptkbp:instanceOf
|
gptkb:algorithm
|
|
gptkbp:abbreviation
|
gptkb:MCTS
|
|
gptkbp:advantage
|
asymptotic optimality
domain independence
|
|
gptkbp:category
|
gptkb:algorithm
gptkb:search_engine
gptkb:reinforcement_learning_technique
|
|
gptkbp:component
|
gptkb:AlphaZero
gptkb:AlphaGo
|
|
gptkbp:describedBy
|
gptkb:Coulom,_2006,_'Efficient_Selectivity_and_Backup_Operators_in_Monte-Carlo_Tree_Search'
|
|
gptkbp:field
|
gptkb:artificial_intelligence
computer science
|
|
gptkbp:hasComponent
|
default policy
rollout
tree policy
value update
|
|
gptkbp:hasVariant
|
gptkb:RAVE
gptkb:Nested_MCTS
gptkb:PUCT
Parallel MCTS
|
|
gptkbp:influenced
|
modern AI game agents
|
|
gptkbp:influencedBy
|
gptkb:Monte_Carlo_method
gptkb:reinforcement_learning
minimax search
|
|
gptkbp:introducedIn
|
2006
|
|
gptkbp:inventedBy
|
gptkb:Rémi_Coulom
|
|
gptkbp:limitation
|
high computational cost
difficulty with sparse rewards
|
|
gptkbp:notableFor
|
gptkb:Go
gptkb:General_Game_Playing
Chess
|
|
gptkbp:openSource
|
gptkb:OpenAI_Gym
Python MCTS libraries
|
|
gptkbp:relatedTo
|
gptkb:Monte_Carlo_method
gptkb:UCT_algorithm
tree search
|
|
gptkbp:step
|
gptkb:simulation
gptkb:expansion
backpropagation
selection
|
|
gptkbp:usedIn
|
planning
robotics
optimization
game playing
|
|
gptkbp:uses
|
gptkb:statistical_analysis
random sampling
|
|
gptkbp:bfsParent
|
gptkb:Dr._Simon_Lucas
gptkb:game_AI
gptkb:ShashChess
gptkb:Reinforcement_Learning_and_Simulation-Based_Search_in_Computer_Go
gptkb:Joel_Veness
|
|
gptkbp:bfsLayer
|
7
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Monte Carlo Tree Search
|