Policy-based optimization: single-step policy gradient method seen as an evolution strategy.
Jonathan ViqueratR. DuvigneauP. MeligaAlexander KuhnleElie HachemPublished in: Neural Comput. Appl. (2023)
Keyphrases
- evolution strategy
- single step
- gradient method
- evolutionary algorithm
- optimization methods
- policy gradient
- actor critic
- differential evolution
- optimization problems
- global optimization
- optimization method
- optimization process
- global search
- optimization algorithm
- negative matrix factorization
- nearest neighbor
- active learning
- multiresolution
- machine learning