Prototypical Reward Network for Data-Efficient RLHF.
Jinghan ZhangXiting WangYiqiao JinChangyu ChenXinhao ZhangKunpeng LiuPublished in: CoRR (2024)
Keyphrases
- data sets
- data analysis
- database
- raw data
- data distribution
- data collection
- image data
- synthetic data
- data sources
- prior knowledge
- multimedia data
- data processing
- data transfer
- reinforcement learning
- network structure
- neural network
- original data
- data quality
- complex networks
- network bandwidth
- network model
- communication networks
- knowledge discovery
- experimental data
- statistical analysis
- probability distribution