A phased game algorithm combining deep reinforcement learning and UCT for Tibetan Jiu chess.
Xiali LiYandong ChenYanyin ZhangBo LiuLicheng WuPublished in: COMPSAC (2023)
Keyphrases
- learning algorithm
- dynamic programming
- monte carlo
- detection algorithm
- computational complexity
- reinforcement learning
- optimization algorithm
- probabilistic model
- alpha beta search
- np hard
- search space
- preprocessing
- objective function
- function approximation
- path planning
- segmentation algorithm
- game playing
- computer games
- computational cost
- matching algorithm
- expectation maximization
- k means
- optimal solution
- decision trees
- artificial intelligence