Publications

Authors:

Marzari, Luca; Trotti, Francesco; Dal Santo, Francesco; Zhalehmehrabi, Amirhossein; Veronese, Celeste; Villaboni, Davide; Bianchi, Federico; Meli, Daniele; Castellini, Alberto; Farinelli, Alessandro

Title:

Enhancing Safety and Explainability of Reinforcement Learning Agents for Environmental Monitoring Tasks

Year:

2025

Type of item:

Contributo in atti di convegno

Tipologia ANVUR:

Contributo in Atti di convegno

Language:

Inglese

Name of journal:

CEUR WORKSHOP PROCEEDINGS

ISSN of journal:

1613-0073

N° Volume:

4121

Congresso:

Proc. Ital-IA 2025: 5th National Conference on Artificial Intelligence, organized by CINI

Place:

Trieste

Period:

June 23–24

:

CEUR-WS.org

Publisher:

CEUR-WS.org

Page numbers:

1-6

Keyword:

Safe Reinforcement Learning, Formal Verification of Neural Networks, Explainable and Neurosymbolic AI, Safe Deployment

Short description of contents:

Mitigating pollution in aquatic ecosystems is among the most pressing challenges in environmental sustainabil- ity applications. While effective monitoring and intervention activities are key to safeguarding water quality, protecting biodiversity, and supporting industries (e.g., aquaculture), this is traditionally done by human oper- ators—making the process costly, time-consuming, and often inadequate for capturing timely environmental changes. In this work, we focus on safe, explainable design and deployment of autonomous reinforcement learning (RL) agents for environmental monitoring tasks. In particular, we present our recent contributions to: i) safe RL techniques, ii) Neurosymbolic RL, iii) formal verification of deep RL policies, and iv) designing robust control strategies for safe deployment.

Web page:

https://ceur-ws.org/Vol-4121/Ital-IA_2025_paper_10.pdf

Product ID:

150462

Handle IRIS:

11562/1187035

Last Modified:

March 25, 2026

Bibliographic citation:

Marzari, Luca; Trotti, Francesco; Dal Santo, Francesco; Zhalehmehrabi, Amirhossein; Veronese, Celeste; Villaboni, Davide; Bianchi, Federico; Meli, Daniele; Castellini, Alberto; Farinelli, Alessandro, Enhancing Safety and Explainability of Reinforcement Learning Agents for Environmental Monitoring Tasks in «CEUR WORKSHOP PROCEEDINGS» vol. 4121 CEUR-WS.org  in Proc. Ital-IA 2025: 5th National Conference on Artificial Intelligence, organized by CINI , CEUR-WS.org , Proceedings of "Proc. Ital-IA 2025: 5th National Conference on Artificial Intelligence, organized by CINI" , Trieste , June 23–24 , 2025 , pp. 1-6

Consulta la scheda completa presente nel repository istituzionale della Ricerca di Ateneo