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

Daesol Cho Seungjae Lee H. Jin Kim

Published in: NeurIPS (2023)

Keyphrases

reinforcement learning
function approximation
machine learning
probabilistic model
data distribution
language learning
probability density function
high school
power law
neural network
cooperative
learning problems
professional development
spatial distribution