Multistage Temporal Difference Learning for 2048-Like Games.
Kun-Hao YehI-Chen WuChu-Hsuan HsuehChia-Chuan ChangChao-Chin LiangHan ChiangPublished in: IEEE Trans. Comput. Intell. AI Games (2017)
Keyphrases
- multistage
- temporal difference learning
- game playing
- monte carlo tree search
- function approximation
- evaluation function
- fixed point
- single stage
- video games
- reinforcement learning
- dynamic programming
- stochastic programming
- temporal difference
- game play
- optimal policy
- reinforcement learning algorithms
- markov decision process
- computer games
- linear programming
- monte carlo
- neural network
- machine learning