# A Local Information Aggregation based Multi-Agent Reinforcement Learning for Robot Swarm Dynamic Task Allocation

arXiv: https://arxiv.org/abs/2411.19526 · HTML: https://mlsanity.com/paper/2411.19526/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 57 references that are in the map.
- First posted on arXiv 29 Nov 2024.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Prioritized Experience Replay](https://mlsanity.com/paper/1511.05952/) (2015)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Actor-Attention-Critic for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1810.02912/) (2018)
- [Mean Field Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1802.05438/) (2018)
- [LINDA: Multi-Agent Local Information Decomposition for Awareness of Teammates](https://mlsanity.com/paper/2109.12508/) (2021)
- [Anonymous Hedonic Game for Task Allocation in a Large-Scale Multiple Agent System](https://mlsanity.com/paper/1711.06871/) (2017)
- [Target Assignment in Robotic Networks: Distance Optimality Guarantees and Hierarchical Strategies](https://mlsanity.com/paper/1308.3956/) (2013)
- [Decentralized Goal Assignment and Safe Trajectory Generation in Multi-Robot Networks via Multiple Lyapunov Functions](https://mlsanity.com/paper/1402.3735/) (2014)
- [Using Affect as a Communication Modality to Improve Human-Robot Communication in Robot-Assisted Search and Rescue Scenarios](https://mlsanity.com/paper/2208.09580/) (2022)

## Built on by (most cited first, 6 of 6)

- [Learning Approximate Nash Equilibria in Cooperative Multi-Agent Reinforcement Learning via Mean-Field Subsampling](https://mlsanity.com/paper/2603.03759/) (2026)
- [Towards Fault Tolerance in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2412.00534/) (2024)
- [Graphon Mean-Field Subsampling for Cooperative Heterogeneous Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2602.16196/) (2026)
- [Spatiotemporal Attention-Augmented Inverse Reinforcement Learning for Multi-Agent Task Allocation](https://mlsanity.com/paper/2504.05045/) (2025)
- [Constrained Black-Box Attacks Against Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2508.09275/) (2025)
- [Fault-Tolerant MARL for CAVs under Observation Perturbations for Highway On-Ramp Merging](https://mlsanity.com/paper/2511.23193/) (2025)

## Abstract (arXiv)

In this paper, we explore how to optimize task allocation for robot swarms in dynamic environments, emphasizing the necessity of formulating robust, flexible, and scalable strategies for robot cooperation. We introduce a novel framework using a decentralized partially observable Markov decision process (Dec_POMDP), specifically designed for distributed robot swarm networks. At the core of our methodology is the Local Information Aggregation Multi-Agent Deep Deterministic Policy Gradient (LIA_MADDPG) algorithm, which merges centralized training with distributed execution (CTDE). During the centralized training phase, a local information aggregation (LIA) module is meticulously designed to gather critical data from neighboring robots, enhancing decision-making efficiency. In the distributed execution phase, a strategy improvement method is proposed to dynamically adjust task allocation based on changing and partially observable environmental conditions. Our empirical evaluations show that the LIA module can be seamlessly integrated into various CTDE-based MARL methods, significantly enhancing their performance. Additionally, by comparing LIA_MADDPG with six conventional reinforcement learning algorithms and a heuristic algorithm, we demonstrate its superior scalability, rapid adaptation to environmental changes, and ability to maintain both stability and convergence speed. These results underscore LIA_MADDPG's outstanding performance and its potential to significantly improve dynamic task allocation in robot swarms through enhanced local collaboration and adaptive strategy execution.