Multi-Agent Reinforcement Learning (MARL) encompasses a powerful class of methodologies that have been applied in a wide range of fields. An effective way to further empower these methodologies is to develop approaches and tools that could expand their interpretability and explainability. In this work, we introduce MARLeME: a MARL model extraction library, designed to improve explainability of MARL systems by approximating them with symbolic models. Symbolic models offer a high degree of interpretability, well-defined properties, and verifiable behaviour. Consequently, they can be used to inspect and better understand the underlying MARL systems and corresponding MARL agents, as well as to replace all/some of the agents that are particularly safety and security critical. In this work, we demonstrate how MARLeME can be applied to two well-known case studies (Cooperative Navigation and RoboCup Takeaway), using extracted models based on Abstract Argumentation.
MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library / Kazhdan, D.; Shams, Z.; Lio, P.. - (2020). (Intervento presentato al convegno 2020 International Joint Conference on Neural Networks, IJCNN 2020 tenutosi a Virtual, Glasgow) [10.1109/IJCNN48605.2020.9207564].
MARLeME: A Multi-Agent Reinforcement Learning Model Extraction Library
Lio P.
2020
Abstract
Multi-Agent Reinforcement Learning (MARL) encompasses a powerful class of methodologies that have been applied in a wide range of fields. An effective way to further empower these methodologies is to develop approaches and tools that could expand their interpretability and explainability. In this work, we introduce MARLeME: a MARL model extraction library, designed to improve explainability of MARL systems by approximating them with symbolic models. Symbolic models offer a high degree of interpretability, well-defined properties, and verifiable behaviour. Consequently, they can be used to inspect and better understand the underlying MARL systems and corresponding MARL agents, as well as to replace all/some of the agents that are particularly safety and security critical. In this work, we demonstrate how MARLeME can be applied to two well-known case studies (Cooperative Navigation and RoboCup Takeaway), using extracted models based on Abstract Argumentation.File | Dimensione | Formato | |
---|---|---|---|
Kazhdan_MARLeME_2020.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
981.71 kB
Formato
Adobe PDF
|
981.71 kB | Adobe PDF | Contatta l'autore |
Kazhdan_preprint_MARLeME_2020.pdf
accesso aperto
Note: DOI: 10.1109/IJCNN48605.2020.9207564
Tipologia:
Documento in Pre-print (manoscritto inviato all'editore, precedente alla peer review)
Licenza:
Creative commons
Dimensione
511.31 kB
Formato
Adobe PDF
|
511.31 kB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.