Evaluating Reinforcement Learning Safety and Trustworthiness in Cyber-Physical Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929756048457728 |
|---|---|
| author | Dearstyne, Katherine Pedro Granadeno, Alarcon Chambers, Theodore Cleland-Huang, Jane |
| author_facet | Dearstyne, Katherine Pedro Granadeno, Alarcon Chambers, Theodore Cleland-Huang, Jane |
| contents | Cyber-Physical Systems (CPS) often leverage Reinforcement Learning (RL) techniques to adapt dynamically to changing environments and optimize performance. However, it is challenging to construct safety cases for RL components. We therefore propose the SAFE-RL (Safety and Accountability Framework for Evaluating Reinforcement Learning) for supporting the development, validation, and safe deployment of RL-based CPS. We adopt a design science approach to construct the framework and demonstrate its use in three RL applications in small Uncrewed Aerial systems (sUAS) |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09388 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evaluating Reinforcement Learning Safety and Trustworthiness in Cyber-Physical Systems Dearstyne, Katherine Pedro Granadeno, Alarcon Chambers, Theodore Cleland-Huang, Jane Software Engineering Machine Learning Cyber-Physical Systems (CPS) often leverage Reinforcement Learning (RL) techniques to adapt dynamically to changing environments and optimize performance. However, it is challenging to construct safety cases for RL components. We therefore propose the SAFE-RL (Safety and Accountability Framework for Evaluating Reinforcement Learning) for supporting the development, validation, and safe deployment of RL-based CPS. We adopt a design science approach to construct the framework and demonstrate its use in three RL applications in small Uncrewed Aerial systems (sUAS) |
| title | Evaluating Reinforcement Learning Safety and Trustworthiness in Cyber-Physical Systems |
| topic | Software Engineering Machine Learning |
| url | https://arxiv.org/abs/2503.09388 |