File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)

Conference Paper: On Reinforcement Learning in Stabilizability of Probabilistic Boolean Control Networks

TitleOn Reinforcement Learning in Stabilizability of Probabilistic Boolean Control Networks
Authors
KeywordsLogical Control Networks
Probability Estimation
reinforcement Learning
Stabilizability
Issue Date28-Nov-2023
PublisherIEEE
Abstract

This paper examines the stabilizability probability of probabilistic Boolean control networks (PBCNs) by utilizing reinforcement learning. The bounds of the reachability probability are formulated based on the algebraic state space representation (ASSR) of PBCNs, which leads to the stabilizability criterion. Furthermore, the equivalence between the stabilizability probability and the optimal state-value function in the form of an iteration equation is proved. The Q-learning technique is implemented to estimate the stabilizability probability and obtain the corresponding optimal control sequences. Theoretical results are demonstrated through an apoptosis network to elaborate on the findings.


Persistent Identifierhttp://hdl.handle.net/10722/341761

 

DC FieldValueLanguage
dc.contributor.authorLin, Lin-
dc.contributor.authorLam, James-
dc.contributor.authorShi, Peng-
dc.contributor.authorNg, Michael K-
dc.contributor.authorLam, Hak-Keung-
dc.date.accessioned2024-03-26T05:36:59Z-
dc.date.available2024-03-26T05:36:59Z-
dc.date.issued2023-11-28-
dc.identifier.urihttp://hdl.handle.net/10722/341761-
dc.description.abstract<p>This paper examines the stabilizability probability of probabilistic Boolean control networks (PBCNs) by utilizing reinforcement learning. The bounds of the reachability probability are formulated based on the algebraic state space representation (ASSR) of PBCNs, which leads to the stabilizability criterion. Furthermore, the equivalence between the stabilizability probability and the optimal state-value function in the form of an iteration equation is proved. The Q-learning technique is implemented to estimate the stabilizability probability and obtain the corresponding optimal control sequences. Theoretical results are demonstrated through an apoptosis network to elaborate on the findings.<br></p>-
dc.languageeng-
dc.publisherIEEE-
dc.relation.ispartof2023 International Conference on Machine Learning and Cybernetics (ICMLC) (09/07/2023-11/07/2023, , , Adelaide)-
dc.subjectLogical Control Networks-
dc.subjectProbability Estimation-
dc.subjectreinforcement Learning-
dc.subjectStabilizability-
dc.titleOn Reinforcement Learning in Stabilizability of Probabilistic Boolean Control Networks-
dc.typeConference_Paper-
dc.identifier.doi10.1109/ICMLC58545.2023.10327924-
dc.identifier.scopuseid_2-s2.0-85179847082-
dc.identifier.spage295-
dc.identifier.epage302-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats