Login / Signup
A model-free sampling method for basins of attraction using hybrid active learning (HAL).
Xue-She Wang
Samuel A. Moore
James D. Turner
Brian P. Mann
Published in:
Commun. Nonlinear Sci. Numer. Simul. (2022)
Keyphrases
</>
model free
active learning
reinforcement learning
reinforcement learning algorithms
temporal difference
function approximation
policy iteration
learning algorithm
semi supervised
unlabeled data
transfer learning
rl algorithms
average reward
fixed point
training examples
labeled data
training set
feature selection