An online actor-critic learning approach with Levenberg-Marquardt algorithm.
Zhen NiHaibo HeDanil V. ProkhorovJian FuPublished in: IJCNN (2011)
Keyphrases
- levenberg marquardt
- actor critic
- learning algorithm
- reinforcement learning
- bundle adjustment
- objective function
- dynamic programming
- back propagation
- optimal solution
- convergence rate
- approximate dynamic programming
- policy gradient
- least squares
- simulated annealing
- structure from motion
- training algorithm
- machine learning
- learning problems
- learning tasks
- function approximation
- optimal control
- neural network
- training process
- particle swarm optimization
- semi supervised
- gradient method
- control system
- learning process