A Dynamic Algorithm Configuration Framework Using Combinatorial Problem Features and Reinforcement Learning.
Elmar SteinerUlrich PferschyPublished in: MIC (2) (2024)
Keyphrases
- dynamic programming
- learning algorithm
- reinforcement learning
- preprocessing
- search space
- optimization algorithm
- path planning
- computational complexity
- objective function
- k means
- key features
- detection algorithm
- segmentation algorithm
- cost function
- computational geometry
- particle swarm optimization
- worst case
- computational cost
- significant improvement
- feature vectors
- feature space
- optimal solution
- false positives
- classification method
- similarity measure
- feature extraction
- recognition algorithm
- function approximation
- decision trees