Efficient (Soft) Q-Learning for Text Generation with Limited Good Data.
Han GuoBowen TanZhengzhong LiuEric P. XingZhiting HuPublished in: EMNLP (Findings) (2022)
Keyphrases
- training data
- data sets
- data analysis
- data mining techniques
- image data
- knowledge discovery
- data structure
- high quality
- computer systems
- text generation
- human subjects
- original data
- synthetic data
- statistical analysis
- cooperative
- data collection
- data processing
- raw data
- multi agent
- data quality
- end users
- limited memory
- mobile robot