A learner-verifier framework for neural network controllers and certificates of stochastic systems
Reinforcement learning has received much attention for learning controllers of deterministic systems. We consider a learner-verifer framework for stochastic control systems and survey recent methods that formally guarantee a conjunction of reachability and safety properties. Given a property and a l...
Saved in:
Main Authors: | CHATTERJEE, Krishnendu, HENZINGER, Thomas A., ZIKELIC, Dorde |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2023
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9058 https://ink.library.smu.edu.sg/context/sis_research/article/10061/viewcontent/978_3_031_30823_9.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Learning provably stabilizing neural controllers for discrete-time stochastic systems
by: ANSARIPOUR, Matin, et al.
Published: (2023) -
Stability verification in stochastic control systems via neural network supermartingales
by: LECHNER, Mathias, et al.
Published: (2024) -
Certified policy verification and synthesis for MDPs under distributional reach-avoidance properties
by: AKSHAY, S., et al.
Published: (2024) -
Stochastic invariants for probabilistic termination
by: CHATTERJEE, Krishnendu, et al.
Published: (2017) -
Infinite time horizon safety of Bayesian neural networks
by: LECHNER, Mathias, et al.
Published: (2021)