A Parallel Framework of Adaptive Dynamic Programming Algorithm With Off-Policy Learning

In this article, a model-free online adaptive dynamic programming (ADP) approach is developed for solving the optimal control problem of nonaffine nonlinear systems. Combining the off-policy learning mechanism with the parallel paradigm, multithread agents are employed to collect the transitions by...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transaction on neural networks and learning systems Jg. 32; H. 8; S. 3578 - 3587
Hauptverfasser: Sun, Changyin, Li, Xiaofeng, Sun, Yuewen
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 01.08.2021
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Adaptive algorithms
Adaptive control
Adaptive dynamic programming (ADP)
Algorithms
Control stability
Control theory
Convergence
Dynamic programming
Heuristic algorithms
Iterative methods
Learning systems
Machine learning
Neural networks
Nonlinear systems
off-policy learning
Optimal control
policy gradient
sample efficiency
Sampled data
Stability analysis
ISSN:2162-237X, 2162-2388, 2162-2388
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this article, a model-free online adaptive dynamic programming (ADP) approach is developed for solving the optimal control problem of nonaffine nonlinear systems. Combining the off-policy learning mechanism with the parallel paradigm, multithread agents are employed to collect the transitions by interacting with the environment that significantly augments the number of sampled data. On the other hand, each thread agent explores the environment with different initial states under its own behavior policy that enhances the exploration capability and alleviates the correlation between the sampled data. After the policy evaluation process, only one step update is required for policy improvement based on the policy gradient method. The stability of the system under iterative control laws is guaranteed. Moreover, the convergence analysis is given to prove that the iterative Q-function is monotonically nonincreasing and finally converges to the solution of the Hamilton-Jacobi-Bellman (HJB) equation. For implementing the algorithm, the actor-critic (AC) structure is utilized with two neural networks (NNs) to approximate the Q-function and the control policy. Finally, the effectiveness of the proposed algorithm is verified by two numerical examples.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2020.3015767