Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning.
Ruo-Ze LiuHaifeng GuoXiaozhong JiYang YuZhen-Jia PangZitai XiaoYuzhou WuTong LuPublished in: IEEE Trans. Games (2022)
Keyphrases
- transfer learning
- reinforcement learning
- learning tasks
- knowledge transfer
- previously learned
- labeled data
- cross domain
- structure learning
- machine learning algorithms
- target domain
- transfer knowledge
- learning algorithm
- machine learning
- manifold alignment
- reinforcement learning agents
- logistic regression
- transferring knowledge
- unlabeled data
- prior knowledge
- data sets
- semi supervised learning
- model selection
- multi task
- expectation maximization
- text classification
- domain specific
- collaborative filtering
- multi task learning
- active learning
- recommender systems
- feature extraction
- tabula rasa