Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data.
Ruiqi ZhangAndrea ZanettePublished in: NeurIPS (2023)
Keyphrases
- data sets
- reinforcement learning
- data analysis
- data collection
- training data
- statistical analysis
- data points
- database
- data quality
- data distribution
- data sources
- image data
- real time
- original data
- raw data
- data mining techniques
- prior knowledge
- learning process
- data structure
- end users
- data processing
- high dimensional data
- missing data
- experimental data
- database systems
- case study
- learning algorithm
- model free
- data integrity
- policy search