Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning.
Yang YueBingyi KangZhongwen XuGao HuangShuicheng YanPublished in: AAAI (2023)
Keyphrases
- reinforcement learning
- data sets
- prior knowledge
- learning systems
- learning algorithm
- data quality
- training data
- synthetic data
- machine learning
- raw data
- learning process
- image data
- data collection
- database
- statistical analysis
- learning problems
- data distribution
- background knowledge
- data points
- data sources
- active learning
- high quality
- labeled data
- learning tasks
- human experts
- data analysis
- original data
- function approximation
- learning models
- action selection
- learning capabilities