CoRe-MARL: Cooperative Redistribution Under Unknown Dynamics Using Recurrent Multi-Agent Reinforcement Learning
This research provides a framework for improving supply distribution in emergency management scenarios, which is relevant for any organization dealing with resource allocation under uncertainty.
This study develops CoRe-MARL, a cooperative multi-agent reinforcement learning (MARL) framework, to address supply imbalances in emergency management.
The framework uses a recurrent network to capture evolving supply and demand dynamics without direct observation.
It is evaluated in a simulated environment and compared to recurrent independent PPO and a local-only heuristic.
The results show that CoRe-MARL reduces the service gap across local centers and enhances service for the worst-served center.
Emergency management assistance programs, such as relief distribution, are essential for delivering necessary supplies to affected communities. However, these programs operate in a decentralized network of local centers that face uncertain local demand and supply dynamics, resulting in inconsistent avail- ability of local services. Redistribution of supplies among these local centers reduces these imbalances, but the centers often make decisions independently, with limited information and disrupted transportation. This study develops CoRe-MARL, a cooperative multi-agent reinforcement learning (MARL) framework, by formulating a decentralized partially observable Markov decision process (Dec-POMDP). We treat each center as an agent that learns a redistribution policy to improve the service in the worst-case region and reduce the service gap across regions while protecting network-wide service. We incorporate a recurrent network that captures evolving supply and demand dynamics without direct observation, while multi-agent proximal policy optimization (MAPPO) enables centralized training and decentralized execution (CTDE). We evaluate the framework in a simulated environment with diverse trajectories, where exact dynamics are not observed by actors and the MAPPO critic. We compare the recurrent MAPPO with the recurrent independent PPO (IPPO) and a local only heuristic, and find that MAPPO reduces the service gap across local centers and enhances service for the worst-served center while maintaining competitive network-wide service. The recurrent MAPPO also shows consistent performance across diverse trajectory patterns, demonstrating its ability to adapt to evolving dynamics. The findings demonstrate the capability of cooperative learning for decentralized redistribution and improving equitable service under uncertain and evolving dynamics.
This report is categorized under AITOP's "Papers" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include CoRe-MARL, multi-agent reinforcement learning.
Source attribution: curated from arXiv cs.AI (@Naimur Rahman Chowdhury, Shatabdi Sen Prapti, Md. Salehin Seyam, Limon Bin Hossain).
