MARLIN: Multi-Agent Reinforcement Learning with Murmuration Intelligence and LLM Guidance for Reservoir Management

2025/09/29 by Heming Fu, Shan Lin, Fu, Heming +3
Computer Science · Engineering · #Data Stream Mining Techniques #FOS: Computer and information sciences #FOS: Electrical engineering #Multiagent Systems (cs.MA) #Reinforcement Learning in Robotics #Reservoir Engineering and Simulation Methods #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2509.25034

openalex publication_date 2025/09/29 · openalex created_date 2025/10/19 · openalex updated_date 2026/07/28

Abstract

As climate change intensifies extreme weather events, water disasters pose growing threats to global communities, making adaptive reservoir management critical for protecting vulnerable populations and ensuring water security. Modern water resource management faces unprecedented challenges from cascading uncertainties propagating through interconnected reservoir networks. These uncertainties, rooted in physical water transfer losses and environmental variability, make precise control difficult. For example, sending 10 tons downstream may yield only 8-12 tons due to evaporation and seepage. Traditional centralized optimization approaches suffer from exponential computational complexity and cannot effectively handle such real-world uncertainties, while existing multi-agent reinforcement learning (MARL) methods fail to achieve effective coordination under uncertainty. To address these challenges, we present MARLIN, a decentralized reservoir management framework inspired by starling murmurations intelligence. Integrating bio-inspired alignment, separation, and cohesion rules with MARL, MARLIN enables individual reservoirs to make local decisions while achieving emergent global coordination. In addition, a LLM provides real-time reward shaping signals, guiding agents to adapt to environmental changes and human-defined preferences. Experiments on USGS data show that MARLIN improves uncertainty handling by 23%, cuts computation by 35%, and accelerates flood response by 68%, exhibiting super-linear coordination, with complexity scaling 5.4x from 400 to 10,000 nodes. These results demonstrate MARLIN's potential for disaster prevention and protecting communities through intelligent, scalable water resource management.

Citations

• VORTEX: Aligning Task Utility and Human Preferences through LLM-Guided Reward Shaping
• Multi-Agent Reinforcement Learning for Decentralized Reservoir Management via Murmuration Intelligence
• Rule-Bottleneck Reinforcement Learning: Joint Explanation and Decision Optimization for Resource Allocation with Language Agents
• Eureka: Human-Level Reward Design via Coding Large Language Models
• Robust Multi-Agent Reinforcement Learning with State Uncertainty
• The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games
• PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards
• Using Natural Language for Reward Shaping in Reinforcement Learning
• QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• Learning Multiagent Communication with Backpropagation

Related

• Multi-Agent Reinforcement Learning for Decentralized Reservoir Management via Murmuration Intelligence
• Fill-and-Spill: Deep Reinforcement Learning Policy Gradient Methods for Reservoir Operation Decision and Control
• Multi-Asset Closed-Loop Reservoir Management Using Deep Reinforcement Learning
• Multi-Objective Reinforcement Learning for Water Management
• Long-Term Mapping of the Douro River Plume with Multi-Agent Reinforcement Learning