File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/TNNLS.2020.3022950
- Scopus: eid_2-s2.0-85117246511
- PMID: 32966221
- WOS: WOS:000704111000026
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Disturbance-Aware Neuro-Optimal System Control Using Generative Adversarial Control Networks
Title | Disturbance-Aware Neuro-Optimal System Control Using Generative Adversarial Control Networks |
---|---|
Authors | |
Keywords | Adaptive dynamic programming (DP) approximate dynamic programming (ADP) generative adversarial networks (GANs) inverse reinforcement learning (RL) neural networks |
Issue Date | 2021 |
Publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=72 |
Citation | IEEE Transactions on Neural Networks and Learning Systems, 2021, v. 32 n. 10, p. 4565-4576 How to Cite? |
Abstract | Disturbance, which is generally unknown to the controller, is unavoidable in real-world systems and it may affect the expected system state and output. Existing control methods, like robust model predictive control, can produce robust solutions to maintain the system stability. However, these robust methods trade the solution optimality for stability. In this article, a method called generative adversarial control networks (GACNs) is proposed to train a controller via demonstrations of the optimal controller. By formulating the optimal control problem in the presence of disturbance, the controller trained by GACNs obtains neuro-optimal solutions without knowing the future disturbance and determines the objective function explicitly. A joint loss, composed of the adversarial loss and the least square loss, is designed to be used in the training of the generator. Experimental results on simulated systems with disturbance show that GACNs outperform other compared control methods. |
Persistent Identifier | http://hdl.handle.net/10722/305338 |
ISSN | 2023 Impact Factor: 10.2 2023 SCImago Journal Rankings: 4.170 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | CHU, KF | - |
dc.contributor.author | Lam, AYS | - |
dc.contributor.author | FAN, C | - |
dc.contributor.author | Li, VOK | - |
dc.date.accessioned | 2021-10-20T10:08:00Z | - |
dc.date.available | 2021-10-20T10:08:00Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | IEEE Transactions on Neural Networks and Learning Systems, 2021, v. 32 n. 10, p. 4565-4576 | - |
dc.identifier.issn | 2162-237X | - |
dc.identifier.uri | http://hdl.handle.net/10722/305338 | - |
dc.description.abstract | Disturbance, which is generally unknown to the controller, is unavoidable in real-world systems and it may affect the expected system state and output. Existing control methods, like robust model predictive control, can produce robust solutions to maintain the system stability. However, these robust methods trade the solution optimality for stability. In this article, a method called generative adversarial control networks (GACNs) is proposed to train a controller via demonstrations of the optimal controller. By formulating the optimal control problem in the presence of disturbance, the controller trained by GACNs obtains neuro-optimal solutions without knowing the future disturbance and determines the objective function explicitly. A joint loss, composed of the adversarial loss and the least square loss, is designed to be used in the training of the generator. Experimental results on simulated systems with disturbance show that GACNs outperform other compared control methods. | - |
dc.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/RecentIssue.jsp?punumber=72 | - |
dc.relation.ispartof | IEEE Transactions on Neural Networks and Learning Systems | - |
dc.rights | IEEE Transactions on Neural Networks and Learning Systems. Copyright © Institute of Electrical and Electronics Engineers. | - |
dc.rights | ©20xx IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.subject | Adaptive dynamic programming (DP) | - |
dc.subject | approximate dynamic programming (ADP) | - |
dc.subject | generative adversarial networks (GANs) | - |
dc.subject | inverse reinforcement learning (RL) | - |
dc.subject | neural networks | - |
dc.title | Disturbance-Aware Neuro-Optimal System Control Using Generative Adversarial Control Networks | - |
dc.type | Article | - |
dc.identifier.email | Lam, AYS: ayslam@eee.hku.hk | - |
dc.identifier.email | Li, VOK: vli@eee.hku.hk | - |
dc.identifier.authority | Lam, AYS=rp02083 | - |
dc.identifier.authority | Li, VOK=rp00150 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/TNNLS.2020.3022950 | - |
dc.identifier.pmid | 32966221 | - |
dc.identifier.scopus | eid_2-s2.0-85117246511 | - |
dc.identifier.hkuros | 327643 | - |
dc.identifier.volume | 32 | - |
dc.identifier.issue | 10 | - |
dc.identifier.spage | 4565 | - |
dc.identifier.epage | 4576 | - |
dc.identifier.isi | WOS:000704111000026 | - |
dc.publisher.place | United States | - |