Forced ε-Greedy, an Expansion to the ε-Greedy Action Selection Method.
George AngelopoulosDimitris MetafasPublished in: NiDS (2021)
Keyphrases
- dynamic programming
- detection method
- high accuracy
- cost function
- high precision
- pairwise
- computational cost
- significant improvement
- synthetic data
- clustering method
- probabilistic model
- preprocessing
- search algorithm
- objective function
- feature selection
- robot soccer
- forward selection
- locally optimal
- neural network
- action selection
- decision trees
- real world