A Study of Causal Confusion in Preference-Based Reward Learning.
Jeremy TienJerry Zhi-Yang HeZackory EricksonAnca D. DraganDaniel S. BrownPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- learning process
- learning algorithm
- empirical studies
- neural network
- learning systems
- students learning
- supervised learning
- university students
- subject matter
- learning tasks
- inductive inference
- undergraduate students
- causal structure
- learning theories
- computer assisted instruction
- qualitative models
- mobile learning
- knowledge acquisition
- online learning
- prior knowledge
- bayesian networks
- machine learning