On Reinforcement Learning in Stabilizability of Probabilistic Boolean Control Networks

Lin Lin; James Lam; Peng Shi; Michael K. Ng; Hak Keung Lam

doi:10.1109/ICMLC58545.2023.10327924

On Reinforcement Learning in Stabilizability of Probabilistic Boolean Control Networks

Lin Lin, James Lam, Peng Shi, Michael K. Ng, Hak Keung Lam

Department of Mathematics

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

2 Citations (Scopus)

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.

Original language	English
Title of host publication	Proceedings of 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023
Publisher	IEEE Computer Society
Pages	295-302
Number of pages	8
Edition	1st
ISBN (Electronic)	9798350303780
ISBN (Print)	9798350303797
DOIs	https://doi.org/10.1109/ICMLC58545.2023.10327924
Publication status	Published - 9 Jul 2023
Event	2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023 - Adelaide, Australia Duration: 9 Jul 2023 → 11 Jul 2023 https://ieeexplore.ieee.org/xpl/conhome/10327787/proceeding (Conference proceedings) https://www.icmlc.org/2023.html (Conference website)

Publication series

Name	Proceedings - International Conference on Machine Learning and Cybernetics
ISSN (Print)	2160-133X
ISSN (Electronic)	2160-1348

Conference

Conference	2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023
Country/Territory	Australia
City	Adelaide
Period	9/07/23 → 11/07/23
Internet address	https://ieeexplore.ieee.org/xpl/conhome/10327787/proceeding (Conference proceedings) https://www.icmlc.org/2023.html (Conference website)

User-Defined Keywords

Logical Control Networks
Probability Estimation
reinforcement Learning
Stabilizability

Access to Document

10.1109/ICMLC58545.2023.10327924

Cite this

Lin, L., Lam, J., Shi, P., Ng, M. K., & Lam, H. K. (2023). On Reinforcement Learning in Stabilizability of Probabilistic Boolean Control Networks. In Proceedings of 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023 (1st ed., pp. 295-302). (Proceedings - International Conference on Machine Learning and Cybernetics). IEEE Computer Society. https://doi.org/10.1109/ICMLC58545.2023.10327924

@inproceedings{cbc4d59e65a54b61974de3d0e645c6b5,

title = "On Reinforcement Learning in Stabilizability of Probabilistic Boolean Control Networks",

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.",

keywords = "Logical Control Networks, Probability Estimation, reinforcement Learning, Stabilizability",

author = "Lin Lin and James Lam and Peng Shi and Ng, {Michael K.} and Lam, {Hak Keung}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023 ; Conference date: 09-07-2023 Through 11-07-2023",

year = "2023",

month = jul,

day = "9",

doi = "10.1109/ICMLC58545.2023.10327924",

language = "English",

isbn = "9798350303797",

series = "Proceedings - International Conference on Machine Learning and Cybernetics",

publisher = "IEEE Computer Society",

pages = "295--302",

booktitle = "Proceedings of 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023",

address = "United States",

edition = "1st",

url = "https://ieeexplore.ieee.org/xpl/conhome/10327787/proceeding, https://www.icmlc.org/2023.html",

}

Lin, L, Lam, J, Shi, P, Ng, MK & Lam, HK 2023, On Reinforcement Learning in Stabilizability of Probabilistic Boolean Control Networks. in Proceedings of 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023. 1st edn, Proceedings - International Conference on Machine Learning and Cybernetics, IEEE Computer Society, pp. 295-302, 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023, Adelaide, South Australia, Australia, 9/07/23. https://doi.org/10.1109/ICMLC58545.2023.10327924

On Reinforcement Learning in Stabilizability of Probabilistic Boolean Control Networks. / Lin, Lin; Lam, James; Shi, Peng et al.
Proceedings of 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023. 1st. ed. IEEE Computer Society, 2023. p. 295-302 (Proceedings - International Conference on Machine Learning and Cybernetics).

Research output: Chapter in book/report/conference proceeding › Conference proceeding › peer-review

TY - GEN

T1 - On Reinforcement Learning in Stabilizability of Probabilistic Boolean Control Networks

AU - Lin, Lin

AU - Lam, James

AU - Shi, Peng

AU - Ng, Michael K.

AU - Lam, Hak Keung

PY - 2023/7/9

Y1 - 2023/7/9

N2 - 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.

AB - 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.

KW - Logical Control Networks

KW - Probability Estimation

KW - reinforcement Learning

KW - Stabilizability

UR - http://www.scopus.com/inward/record.url?scp=85179847082&partnerID=8YFLogxK

U2 - 10.1109/ICMLC58545.2023.10327924

DO - 10.1109/ICMLC58545.2023.10327924

M3 - Conference proceeding

AN - SCOPUS:85179847082

SN - 9798350303797

T3 - Proceedings - International Conference on Machine Learning and Cybernetics

SP - 295

EP - 302

BT - Proceedings of 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

PB - IEEE Computer Society

T2 - 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023

Y2 - 9 July 2023 through 11 July 2023

ER -

Lin L, Lam J, Shi P, Ng MK, Lam HK. On Reinforcement Learning in Stabilizability of Probabilistic Boolean Control Networks. In Proceedings of 2023 International Conference on Machine Learning and Cybernetics, ICMLC 2023. 1st ed. IEEE Computer Society. 2023. p. 295-302. (Proceedings - International Conference on Machine Learning and Cybernetics). doi: 10.1109/ICMLC58545.2023.10327924

On Reinforcement Learning in Stabilizability of Probabilistic Boolean Control Networks

Abstract

Publication series

Conference

User-Defined Keywords

Access to Document

Other files and links

Fingerprint

Cite this