Algorithm selection of off-policy reinforcement learning algorithm.
Romain LarocheRaphaël FéraudPublished in: CoRR (2017)
Keyphrases
- computational complexity
- experimental evaluation
- optimization algorithm
- computationally efficient
- preprocessing
- improved algorithm
- selection algorithm
- high accuracy
- detection algorithm
- estimation algorithm
- cost function
- computational cost
- probabilistic model
- experimental study
- clustering method
- simulated annealing
- optimal solution
- learning algorithm
- times faster
- objective function
- segmentation algorithm
- worst case
- significant improvement
- scheduling problem
- matching algorithm
- np hard
- k means
- artificial neural networks
- space complexity
- single pass