Learning to summarize with human feedback.
Nisan StiennonLong OuyangJeffrey WuDaniel M. ZieglerRyan LoweChelsea VossAlec RadfordDario AmodeiPaul F. ChristianoPublished in: NeurIPS (2020)
Keyphrases
- learning systems
- learning problems
- feedback mechanisms
- learning process
- artificial intelligence
- language acquisition
- unsupervised learning
- online learning
- prior knowledge
- information retrieval
- learning experience
- learning environment
- human experts
- learning scheme
- decision trees
- human computer
- motor skills
- tutorial dialogue