Disentangling Policy from Offline Task Representation Learning via Adversarial Data Augmentation.
Chengxing JiaFuxiang ZhangYi-Chen LiChenxiao GaoXu-Hui LiuLei YuanZongzhang ZhangYang YuPublished in: CoRR (2024)
Keyphrases
- data sets
- data analysis
- database
- image data
- learning tasks
- training data
- high quality
- prior knowledge
- background knowledge
- synthetic data
- data sources
- supervised learning
- data mining techniques
- human experts
- unsupervised learning
- data processing
- learning process
- data structure
- knowledge discovery
- sensor data
- policy gradient
- bayesian methods
- learning models
- original data
- databases
- machine learning
- data distribution
- experimental data
- data mining algorithms
- knowledge base
- high dimensional data
- data collection
- probabilistic model
- input data
- data points