Discrete-time generalized policy iteration ADP algorithm with approximation errors
- Resource Type
- Authors
- Ruizhuo Song; Qinglai Wei; Benkai Li
- Source
- SSCI
- Subject
- Artificial neural network
Computer science
020208 electrical & electronic engineering
Astrophysics::Instrumentation and Methods for Astrophysics
02 engineering and technology
Function (mathematics)
Optimal control
Nonlinear system
Discrete time and continuous time
Bellman equation
Convergence (routing)
0202 electrical engineering, electronic engineering, information engineering
Reinforcement learning
020201 artificial intelligence & image processing
Astrophysics::Earth and Planetary Astrophysics
Algorithm
- Language
This paper concerns with a novel generalized policy iteration (GPI) algorithm with approximation errors. Approximation errors are explicitly considered in the GPI algorithm. The properties of the stable GPI algorithm with approximation errors are analyzed. The convergence of the developed algorithm is established to show that the iterative value function is convergent to a finite neighborhood of the optimal performance index function. Finally, numerical examples and comparisons are presented.