A Lyapunov-Guided Post-Action Shield for Stability-Aware Deep Reinforcement Learning
Hyväksytty kirjoittajan käsikirjoitus - 2.92 MB
Kahil, H., Välisuo, P., & Elmusrati, M. (2026). A Lyapunov-Guided Post-Action Shield for Stability-Aware Deep Reinforcement Learning. In 2026 12th International Conference on Control, Decision and Information Technologies (CoDIT), 1649-1654. IEEE. https://doi.org/10.1109/CoDIT70676.2026.11630899
© 2026 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.
Lataukset70
Pysyvä osoite
Kuvaus
This paper proposes a Lyapunov-guided post-action shielding mechanism for deep reinforcement learning (DRL) controllers under bounded actuation disturbances. In addition, an energy-safety requirement is formulated as a one-step energy threshold constraint that keeps the predicted next-state energy proxy within a prescribed limit, using a bounded-disturbance worst-case check. Simulation results show that the proposed mechanism substantially reduces constraint violations under actuation noise while preserving the nominal policy behavior whenever possible.
Emojulkaisu
2026 12th International Conference on Control, Decision and Information Technologies (CoDIT)
ISBN
979-8-3195-2077-7
ISSN
2576-3555
2576-3547
2576-3547
Aihealue
Kausijulkaisu
International conference on control, decision and information technologies
OKM-julkaisutyyppi
A4 Vertaisarvioitu artikkeli konferenssijulkaisussa