HJB equation based learning scheme for neural networks.
Vipul AroraLaxmidhar BeheraTharun Kumar ReddyAjay Pratap YadavPublished in: IJCNN (2017)
Keyphrases
- learning scheme
- hamilton jacobi bellman
- neural network
- optimal control
- control problems
- error back propagation
- nonlinear systems
- fuzzy systems
- learning algorithm
- stochastic control
- dynamical systems
- reinforcement learning
- hamilton jacobi
- approximate dynamic programming
- dynamic programming
- fuzzy logic
- back propagation
- adaptive control
- differential equations
- control strategy
- computational intelligence