Stagewise Newton, differential dynamic programming, and neighboring optimum control for neural-network learning.
Eiji MizutaniStuart E. DreyfusPublished in: ACC (2005)
Keyphrases
- neural network
- dynamic programming
- learning process
- learning systems
- reinforcement learning
- neural nets
- unsupervised learning
- control rules
- optimal control
- multi class
- prior knowledge
- control parameters
- inductive inference
- adaptive control
- markov decision processes
- robot control
- collaborative learning
- knowledge acquisition
- online learning
- linear programming
- active learning
- artificial neural networks
- learning environment
- learning algorithm
- machine learning