Meta-Offline and Distributional Multi-Agent RL for Risk-Aware Decision-Making
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908986260848640 |
|---|---|
| author | Eldeeb, Eslam Alves, Hirley |
| author_facet | Eldeeb, Eslam Alves, Hirley |
| contents | Mission critical applications, such as UAV-assisted IoT networks require risk-aware decision-making under dynamic topologies and uncertain channels. We propose meta-conservative quantile regression (M-CQR), a meta-offline distributional MARL algorithm that integrates conservative Q-learning (CQL) for safe offline learning, quantile regression DQN (QR-DQN) for risk-sensitive value estimation, and model-agnostic meta-learning (MAML) for rapid adaptation. Two variants are developed: meta-independent CQR (M-I-CQR) and meta-CTDE-CQR. In a UAV-based communication scenario, M-CTDE-CQR achieves up to 50% faster convergence and outperforms baseline MARL methods, offering improved scalability, robustness, and adaptability for risk-sensitive decision-making. Code is available at https://github.com/Eslam211/MA_Meta_ODRL |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_16098 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Meta-Offline and Distributional Multi-Agent RL for Risk-Aware Decision-Making Eldeeb, Eslam Alves, Hirley Multiagent Systems Mission critical applications, such as UAV-assisted IoT networks require risk-aware decision-making under dynamic topologies and uncertain channels. We propose meta-conservative quantile regression (M-CQR), a meta-offline distributional MARL algorithm that integrates conservative Q-learning (CQL) for safe offline learning, quantile regression DQN (QR-DQN) for risk-sensitive value estimation, and model-agnostic meta-learning (MAML) for rapid adaptation. Two variants are developed: meta-independent CQR (M-I-CQR) and meta-CTDE-CQR. In a UAV-based communication scenario, M-CTDE-CQR achieves up to 50% faster convergence and outperforms baseline MARL methods, offering improved scalability, robustness, and adaptability for risk-sensitive decision-making. Code is available at https://github.com/Eslam211/MA_Meta_ODRL |
| title | Meta-Offline and Distributional Multi-Agent RL for Risk-Aware Decision-Making |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2501.16098 |