Concept-Based Interpretable Reinforcement Learning with Limited to No Human Labels.

Zhuorui Ye Stephanie Milani Geoffrey J. Gordon Fei Fang

Published in: CoRR (2024)

Keyphrases

reinforcement learning
training data
function approximation
learning algorithm
human subjects
human interaction
artificial intelligence
human activities
reinforcement learning algorithms
neural network
active learning
optimal policy
class labels
action selection