Value-Consistent Representation Learning for Data-Efficient Reinforcement Learning.
Yang YueBingyi KangZhongwen XuGao HuangShuicheng YanPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- data sets
- learning process
- prior knowledge
- learning algorithm
- data sources
- statistical analysis
- raw data
- data analysis
- synthetic data
- high dimensional data
- computer systems
- data collection
- neural network
- background knowledge
- knowledge acquisition
- data structure
- supervised learning
- image data
- learning systems
- data distribution
- data quality
- function approximation
- learning models
- collaborative learning
- state space
- image representation
- active learning
- learning problems
- machine learning