An Efficient Algorithm for Deep Stochastic Contextual Bandits.
Tan ZhuGuannan LiangChunjiang ZhuHaining LiJinbo BiPublished in: CoRR (2021)
Keyphrases
- computational complexity
- monte carlo
- recognition algorithm
- times faster
- cost function
- detection algorithm
- experimental evaluation
- learning algorithm
- improved algorithm
- search space
- input data
- matching algorithm
- neural network
- computational cost
- objective function
- high accuracy
- theoretical analysis
- highly efficient
- np hard
- significant improvement
- convergence rate
- estimation algorithm
- worst case
- selection algorithm
- preprocessing
- k means
- classification algorithm
- dynamic programming
- optimization algorithm
- expectation maximization