Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data.
Ruiqi ZhangAndrea ZanettePublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- data sets
- data analysis
- statistical analysis
- machine learning
- data processing
- training data
- data points
- knowledge discovery
- image data
- xml documents
- high quality
- optimal policy
- data distribution
- raw data
- database
- original data
- data sources
- dynamic programming
- prior knowledge
- user interface
- case study
- neural network
- databases
- data mining techniques
- data collection
- computer systems
- data structure
- synthetic data
- sensor data
- experimental data
- learning algorithm