AE-HNN-NCS embeds deep RL policies into a low-dimensional latent space with an autoencoder and uses a hyperbolic neural network classifier to pre-select candidates, claiming large gains in sample efficiency and final performance.
Artificial Intelligence (2025), 104308
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
REJECT 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Surrogate-Assisted Evolutionary Reinforcement Learning Based on Autoencoder and Hyperbolic Neural Network
AE-HNN-NCS embeds deep RL policies into a low-dimensional latent space with an autoencoder and uses a hyperbolic neural network classifier to pre-select candidates, claiming large gains in sample efficiency and final performance.