An Organizationally-Oriented Approach to Enhancing Explainability and Control in Multi-Agent Reinforcement Learning
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_ | 1866908290560032768 |
|---|---|
| author | Soulé, Julien Jamont, Jean-Paul Occello, Michel Traonouez, Louis-Marie Théron, Paul |
| author_facet | Soulé, Julien Jamont, Jean-Paul Occello, Michel Traonouez, Louis-Marie Théron, Paul |
| contents | Multi-Agent Reinforcement Learning can lead to the development of collaborative agent behaviors that show similarities with organizational concepts. Pushing forward this perspective, we introduce a novel framework that explicitly incorporates organizational roles and goals from the $\mathcal{M}OISE^+$ model into the MARL process, guiding agents to satisfy corresponding organizational constraints. By structuring training with roles and goals, we aim to enhance both the explainability and control of agent behaviors at the organizational level, whereas much of the literature primarily focuses on individual agents. Additionally, our framework includes a post-training analysis method to infer implicit roles and goals, offering insights into emergent agent behaviors. This framework has been applied across various MARL environments and algorithms, demonstrating coherence between predefined organizational specifications and those inferred from trained agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_23615 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | An Organizationally-Oriented Approach to Enhancing Explainability and Control in Multi-Agent Reinforcement Learning Soulé, Julien Jamont, Jean-Paul Occello, Michel Traonouez, Louis-Marie Théron, Paul Artificial Intelligence Machine Learning Multi-Agent Reinforcement Learning can lead to the development of collaborative agent behaviors that show similarities with organizational concepts. Pushing forward this perspective, we introduce a novel framework that explicitly incorporates organizational roles and goals from the $\mathcal{M}OISE^+$ model into the MARL process, guiding agents to satisfy corresponding organizational constraints. By structuring training with roles and goals, we aim to enhance both the explainability and control of agent behaviors at the organizational level, whereas much of the literature primarily focuses on individual agents. Additionally, our framework includes a post-training analysis method to infer implicit roles and goals, offering insights into emergent agent behaviors. This framework has been applied across various MARL environments and algorithms, demonstrating coherence between predefined organizational specifications and those inferred from trained agents. |
| title | An Organizationally-Oriented Approach to Enhancing Explainability and Control in Multi-Agent Reinforcement Learning |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2503.23615 |