Rank Selection Method of CP Decomposition Based on Deep Deterministic Policy Gradient Algorithm.
Shaoshuang ZhangZhao LiWenlong LiuJiaqi ZhaoTing QinPublished in: IEEE Access (2024)
Keyphrases
- dynamic programming
- optimization algorithm
- computational complexity
- cost function
- clustering method
- objective function
- optimization method
- gradient ascent
- learning algorithm
- k means
- support vector machine svm
- path planning
- convergence rate
- optimal solution
- gradient method
- natural gradient
- np hard
- reinforcement learning
- dynamical systems
- clustering algorithm
- model free
- importance sampling
- approximation methods
- neural network