The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types.
Gaurav R. GhosalMatthew ZurekDaniel S. BrownAnca D. DraganPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- learning tasks
- learning algorithm
- learning process
- multiple tasks
- human learning
- learning problems
- knowledge acquisition
- unsupervised learning
- learning systems
- online learning
- human experts
- learning analytics
- active learning
- language acquisition
- motor skills
- individual level
- creative problem solving
- knowledge level
- dynamic bayesian networks
- supervised learning
- e learning