Reinforcement Learning for Algorithm Selection.
Michail G. LagoudakisMichael L. LittmanPublished in: AAAI/IAAI (2000)
Keyphrases
- dynamic programming
- theoretical analysis
- learning algorithm
- reinforcement learning
- detection algorithm
- experimental evaluation
- high accuracy
- improved algorithm
- k means
- worst case
- classification algorithm
- significant improvement
- times faster
- selection algorithm
- objective function
- machine learning
- matching algorithm
- optimization algorithm
- selection strategy
- model free
- computational cost
- np hard
- preprocessing
- computationally efficient
- segmentation algorithm
- probabilistic model
- computational complexity
- recognition algorithm
- optimal solution
- multi robot
- similarity measure
- genetic algorithm
- neural network