Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2504.11569 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910912489717760 |
|---|---|
| author | Fu, Heming Xiong, Guojun Li, Jian Lin, Shan |
| author_facet | Fu, Heming Xiong, Guojun Li, Jian Lin, Shan |
| contents | Conventional centralized water management systems face critical limitations from computational complexity and uncertainty propagation. We present MurmuRL, a novel decentralized framework inspired by starling murmurations intelligence, integrating bio-inspired alignment, separation, and cohesion rules with multi-agent reinforcement learning. MurmuRL enables individual reservoirs to make autonomous local decisions while achieving emergent global coordination. Experiments on grid networks demonstrate that MurmuRL achieves 8.8% higher final performance while using 27% less computing overhead compared to centralized approaches. Notably, strategic diversity scales super-linearly with system size, exhibiting sophisticated coordination patterns and enhanced resilience during extreme events. MurmuRL offers a scalable solution for managing complex water systems by leveraging principles of natural collective behavior. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11569 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multi-Agent Reinforcement Learning for Decentralized Reservoir Management via Murmuration Intelligence Fu, Heming Xiong, Guojun Li, Jian Lin, Shan Systems and Control Conventional centralized water management systems face critical limitations from computational complexity and uncertainty propagation. We present MurmuRL, a novel decentralized framework inspired by starling murmurations intelligence, integrating bio-inspired alignment, separation, and cohesion rules with multi-agent reinforcement learning. MurmuRL enables individual reservoirs to make autonomous local decisions while achieving emergent global coordination. Experiments on grid networks demonstrate that MurmuRL achieves 8.8% higher final performance while using 27% less computing overhead compared to centralized approaches. Notably, strategic diversity scales super-linearly with system size, exhibiting sophisticated coordination patterns and enhanced resilience during extreme events. MurmuRL offers a scalable solution for managing complex water systems by leveraging principles of natural collective behavior. |
| title | Multi-Agent Reinforcement Learning for Decentralized Reservoir Management via Murmuration Intelligence |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2504.11569 |