Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation.
Chengxing JiaFuxiang ZhangYi-Chen LiChenxiao GaoXu-Hui LiuLei YuanZongzhang ZhangYang YuPublished in: AAMAS (2024)
Keyphrases
- data sets
- reinforcement learning
- data processing
- prior knowledge
- statistical analysis
- data collection
- database
- knowledge discovery
- real time
- synthetic data
- learning systems
- background knowledge
- data analysis
- data distribution
- data quality
- missing data
- sensor data
- spatial data
- learning tasks
- knowledge acquisition
- image data
- end users
- data sources
- high quality
- unsupervised learning
- active learning
- data model
- learning algorithm
- human experts
- original data
- neural network
- learning models
- learned models