Journal
AUTOMATICA
Volume 64, Issue -, Pages 94-104Publisher
PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.automatica.2015.10.039
Keywords
Model-based reinforcement learning; Concurrent learning; Simulated experience; Data-based control; Adaptive control; System identification
Funding
- National Science Foundation [1509516]
- Office of Naval Research [N00014-13-1-0151]
- Directorate For Engineering
- Div Of Electrical, Commun & Cyber Sys [1509516] Funding Source: National Science Foundation
- Div Of Civil, Mechanical, & Manufact Inn
- Directorate For Engineering [1161260] Funding Source: National Science Foundation
Ask authors/readers for more resources
Reinforcement learning (RL)-based online approximate optimal control methods applied to deterministic systems typically require a restrictive persistence of excitation (PE) condition for convergence. This paper develops a concurrent learning (CL)-based implementation of model-based RL to solve approximate optimal regulation problems online under a PE-like rank condition. The development is based on the observation that, given a model of the system, RL can be implemented by evaluating the Bellman error at any number of desired points in the state space. In this result, a parametric system model is considered, and a CL-based parameter identifier is developed to compensate for uncertainty in the parameters. Uniformly ultimately bounded regulation of the system states to a neighborhood of the origin, and convergence of the developed policy to a neighborhood of the optimal policy are established using a Lyapunov-based analysis, and simulation results are presented to demonstrate the performance of the developed controller. (C) 2015 Elsevier Ltd. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available