Temporal-Logic-Based Reward Shaping for Continuing Learning Tasks.

Yuqian Jiang Sudarshanan Bharadwaj Bo Wu Rishi Shah Ufuk Topcu Peter Stone

Published in: CoRR (2020)

Keyphrases

learning tasks
reward shaping
learning algorithm
machine learning
supervised learning
transfer learning
function approximation
learning experience
machine learning algorithms
reinforcement learning
learning agent
kernel methods
knowledge representation
multi label
text classification