Survey of Reinforcement Learning based on Human Prior Knowledge.
Zijing GuoChendie YaoYanghe FengYue XuPublished in: J. Uncertain Syst. (2022)
Keyphrases
- prior knowledge
- reinforcement learning
- model free
- training data
- function approximation
- machine learning
- human behavior
- prior information
- learning process
- mobile robot
- data collection
- human activities
- domain knowledge
- bayesian framework
- latent variables
- human subjects
- image sequences
- human users
- human interaction
- data mining