Solution of the linear quadratic regulator problem of black box linear systems using reinforcement learning
| dc.contributor.author | Perrusquía, Adolfo | |
| dc.date.accessioned | 2022-03-23T11:11:35Z | |
| dc.date.available | 2022-03-23T11:11:35Z | |
| dc.date.issued | 2022-03-05 | |
| dc.description.abstract | In this paper, a Q-learning algorithm is proposed to solve the linear quadratic regulator problem of black box linear systems. The algorithm only has access to input and output measurements. A Luenberger observer parametrization is constructed using the control input and a new output obtained from a factorization of the utility function. An integral reinforcement learning approach is used to develop the Q-learning approximator structure. A gradient descent update rule is used to estimate on-line the parameters of the Q-function. Stability and convergence of the Q-learning algorithm under the Luenberger observer parametrization is assessed using Lyapunov stability theory. Simulation studies are carried out to verify the proposed approach. | en_UK |
| dc.identifier.citation | Perrusquia A. (2022) Solution of the linear quadratic regulator problem of black box linear systems using reinforcement learning, Information Sciences, Volume 595, May 2022, pp. 364-377 | en_UK |
| dc.identifier.eissn | 1872-6291 | |
| dc.identifier.issn | 0020-0255 | |
| dc.identifier.uri | https://doi.org/10.1016/j.ins.2022.03.004 | |
| dc.identifier.uri | https://dspace.lib.cranfield.ac.uk/handle/1826/17670 | |
| dc.language.iso | en | en_UK |
| dc.publisher | Elsevier | en_UK |
| dc.rights | Attribution 4.0 International | * |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | * |
| dc.subject | Linear quadratic regulator | en_UK |
| dc.subject | State observer parametrization | en_UK |
| dc.subject | Q-learning | en_UK |
| dc.subject | Gradient descent | en_UK |
| dc.subject | Output feedback | en_UK |
| dc.subject | Persistency of excitation | en_UK |
| dc.title | Solution of the linear quadratic regulator problem of black box linear systems using reinforcement learning | en_UK |
| dc.type | Article | en_UK |