Only-One-Victor Pattern Learning in Computer Go.
Jiao WangChenjun XiaoTan ZhuChu-Hsuan HsuehWen-Jie TsengI-Chen WuPublished in: IEEE Trans. Comput. Intell. AI Games (2017)
Keyphrases
- learning process
- supervised learning
- learning algorithm
- active learning
- learning tasks
- incremental learning
- reinforcement learning
- learning problems
- markov chain
- learning systems
- temporal difference learning
- learning scheme
- learning scenarios
- background knowledge
- empirical studies
- prior knowledge
- multi agent
- bayesian networks
- case study
- decision trees