Diversify & Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement.

Daesol Cho Seungjae Lee H. Jin Kim

Published in: CoRR (2023)

Keyphrases

reinforcement learning
multi agent
cooperative
active learning
high school
spatial distribution
data distribution
learning algorithm
information systems
transfer learning
markov decision processes
function approximation
learning agents