Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction.
Yangqing FuMing SunBuqing NieYue GaoPublished in: NeurIPS (2023)
Keyphrases
- monte carlo tree search
- tree search algorithm
- state abstraction
- monte carlo
- state space
- evaluation function
- game tree
- reinforcement learning
- markov decision processes
- temporal difference
- path finding
- probability distribution
- tree structure
- reinforcement learning algorithms
- initial state
- admissible heuristics
- temporal difference learning
- reinforcement learning methods
- tree search
- b tree