Kim, J (2022) State-space segmentation for faster training reinforcement learning. In: IFAC-PapersOnLine. 10th IFAC Symposium on Robust Control Design ROCOND 2022, 30 Aug - 02 Sep 2022, Kyoto, Japan. Elsevier , pp. 235-240.
Abstract
Nonlinear control problems have been the main subjects in control engineering from theoretical and applicational aspects. Reinforcement learning shows promising results for solving highly nonlinear control problems. Among many variants of reinforcement learning, Deep Deterministic Policy Gradient (DDPG) considers continuous control signals, which makes it an ideal candidate for solving nonlinear control problems. The training requires frequently, however, a large number of computations. To improve the convergence of DDPG, we present a state-space segmentation method dividing the state-space to expand the target space defined by the best reward. An inverted pendulum control example demonstrates the performance of the proposed segmentation method.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. This is an author produced version of an article published in IFAC-PapersOnLine. Uploaded in accordance with the publisher's self-archiving policy. |
Keywords: | reinforcement learning; learning convergence; reward; linear control |
Dates: |
|
Institution: | The University of Leeds |
Academic Units: | The University of Leeds > Faculty of Engineering & Physical Sciences (Leeds) > School of Mechanical Engineering (Leeds) > Institute of Engineering Systems and Design (iESD) (Leeds) |
Funding Information: | Funder Grant number Korea Foundation Not Known |
Depositing User: | Symplectic Publications |
Date Deposited: | 18 Jan 2023 16:45 |
Last Modified: | 19 Jan 2023 09:32 |
Status: | Published |
Publisher: | Elsevier |
Identification Number: | 10.1016/j.ifacol.2022.09.352 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:195158 |