On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling, and Beyond.
Thanh Nguyen-TangRaman AroraPublished in: CoRR (2024)
Keyphrases
- reinforcement learning
- database
- data sets
- data processing
- sampled data
- data structure
- data sources
- original data
- synthetic data
- statistical analysis
- data collection
- probability distribution
- high quality
- training data
- random sample
- data samples
- data analysis
- data distribution
- random samples
- data quality
- spatial and temporal resolution
- raw data
- sample size
- end users
- multi agent
- data mining
- databases
- real time