Reinforcement Learning with Neural Network-based Deterministic Game Tree Approximation.
Kevin PrakashGenya IshigakiPublished in: BigDataService (2023)
Keyphrases
- game tree
- reinforcement learning
- game playing
- alpha beta
- evaluation function
- game tree search
- monte carlo
- search algorithm
- two player games
- neural network
- temporal difference learning
- function approximation
- imperfect information games
- imperfect information
- tree search
- search tree
- optimal policy
- learning algorithm
- machine learning
- optimal strategy
- state space
- learning process
- perfect information
- associative memory
- markov chain