Symbol Guided Hindsight Priors for Reward Learning from Human Preferences.

Mudit Verma Katherine Metcalf

Published in: CoRR (2022)

Keyphrases

reinforcement learning
learning process
human learning
learning systems
learning algorithm
decision making
prior knowledge
supervised learning
learning tasks
online learning
preference learning
data sets
action selection
higher education
learning styles
collaborative filtering
active learning