A Boosting-based Deep Neural Networks Algorithm for Reinforcement Learning.
Yu WangHongxia JinPublished in: ACC (2018)
Keyphrases
- learning algorithm
- reinforcement learning
- neural network
- dynamic programming
- preprocessing
- pattern recognition
- computational complexity
- detection algorithm
- k means
- significant improvement
- optimization algorithm
- worst case
- simulated annealing
- model free
- recognition algorithm
- back propagation
- probabilistic model
- np hard
- linear programming
- expectation maximization
- segmentation algorithm
- computational cost
- matching algorithm
- neural network model
- associative memory
- cost function
- training algorithm
- objective function
- decision tree algorithm
- boosting framework