Data-Driven Model-Free Tracking Reinforcement Learning Control with VRFT-based Adaptive Actor-Critic

Data-Driven Model-Free Tracking Reinforcement Learning Control with VRFT-based Adaptive Actor-Critic

This paper proposes a neural network (NN)-based control scheme in an Adaptive Actor-Critic (AAC) learning framework designed for output reference model tracking, as a representative deep-learning application. The control learning scheme is model-free with respect to the process model. AAC designs us...

Full description

Bibliographic Details
Main Authors: Mircea-Bogdan Radac, Radu-Emil Precup
Format: Article
Language:English
Published: MDPI AG 2019-04-01
Series:Applied Sciences
Subjects:
adaptive actor-critic
model-free control
data-driven control
reinforcement learning
approximate dynamic programming
output reference model tracking
multi-input multi-output systems
vertical tank systems
Virtual Reference Feedback Tuning
Online Access:https://www.mdpi.com/2076-3417/9/9/1807

Internet

https://www.mdpi.com/2076-3417/9/9/1807

Similar Items