Learning control policies for stochastic systems with reach-avoid guarantees
We study the problem of learning controllers for discrete-time non-linear stochastic dynamical systems with formal reach-avoid guarantees. This work presents the first method for providing formal reach-avoid guarantees, which combine and generalize stability and safety guarantees, with a tolerable p...
Saved in:
Main Authors: | ZIKELIC, Dorde, LECHNER, Mathias, HENZINGER, A. Thomas, CHATTERJEE, Krishnendu |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9081 https://ink.library.smu.edu.sg/context/sis_research/article/10084/viewcontent/26407_Article_Text_30470_1_2_20230626.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Compositional policy learning in stochastic control systems with formal guarantees
by: ZIKELIC, Dorde, et al.
Published: (2024) -
Stochastic invariants for probabilistic termination
by: CHATTERJEE, Krishnendu, et al.
Published: (2017) -
Sound and complete certificates for quantitative termination analysis of probabilistic programs
by: CHATTERJEE, Krishnendu, et al.
Published: (2022) -
Stability verification in stochastic control systems via neural network supermartingales
by: LECHNER, Mathias, et al.
Published: (2024) -
Learning provably stabilizing neural controllers for discrete-time stochastic systems
by: ANSARIPOUR, Matin, et al.
Published: (2023)