A Survey of Reinforcement Learning from Human Feedback.
Timo KaufmannPaul WengViktor BengsEyke HüllermeierPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- human operators
- human subjects
- human interaction
- human behavior
- multi agent
- function approximation
- human computer interaction
- motor skills
- learning algorithm
- machine learning
- reward signal
- multi agent reinforcement learning
- sensory inputs
- user engagement
- temporal difference learning
- real time
- robot control
- model free
- human activities
- information processing
- state space
- dynamic programming
- data sets