# Learning Scalable Policies over Graphs for Multi-Robot Task Allocation using Capsule Attention Networks

arXiv: https://arxiv.org/abs/2205.03321 · HTML: https://mlsanity.com/paper/2205.03321/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2022.

## Built on by (most cited first, 10 of 10)

- [Fast Decision Support for Air Traffic Management at Urban Air Mobility Vertiports using Graph Learning](https://mlsanity.com/paper/2308.09075/) (2023)
- [Graph Learning-based Fleet Scheduling for Urban Air Mobility under Operational Constraints, Varying Demand & Uncertainties](https://mlsanity.com/paper/2401.04851/) (2024)
- [Learning Dual-arm Object Rearrangement for Cartesian Robots](https://mlsanity.com/paper/2402.13634/) (2024)
- [Bigraph Matching Weighted with Learnt Incentive Function for Multi-Robot Task Allocation](https://mlsanity.com/paper/2403.07131/) (2024)
- [A Graph-based Adversarial Imitation Learning Framework for Reliable & Realtime Fleet Scheduling in Urban Air Mobility](https://mlsanity.com/paper/2407.12113/) (2024)
- [Spatiotemporal Attention-Augmented Inverse Reinforcement Learning for Multi-Agent Task Allocation](https://mlsanity.com/paper/2504.05045/) (2025)
- [Learning-aided Bigraph Matching Approach to Multi-Crew Restoration of Damaged Power Networks Coupled with Road Transportation Networks](https://mlsanity.com/paper/2506.19703/) (2025)
- [Automated Generation of Diverse Courses of Actions for Multi-Agent Operations using Binary Optimization and Graph Learning](https://mlsanity.com/paper/2506.20031/) (2025)
- [Designing Active Tether-Net Systems for Space Debris Capture with Graph-Learning-Aided Mixed-Combinatorial Optimization](https://mlsanity.com/paper/2605.29021/) (2026)
- [Learning-based Directed Graph Abstraction of Combinatorial Spaces for Order-Preserving Search in Mixed-Combinatorial Nonlinear Optimization](https://mlsanity.com/paper/2606.01425/) (2026)

## Abstract (arXiv)

This paper presents a novel graph reinforcement learning (RL) architecture to solve multi-robot task allocation (MRTA) problems that involve tasks with deadlines and workload, and robot constraints such as work capacity. While drawing motivation from recent graph learning methods that learn to solve combinatorial optimization (CO) problems such as multi-Traveling Salesman and Vehicle Routing Problems using RL, this paper seeks to provide better performance (compared to non-learning methods) and important scalability (compared to existing learning architectures) for the stated class of MRTA problems. The proposed neural architecture, called Capsule Attention-based Mechanism or CapAM acts as the policy network, and includes three main components: 1) an encoder: a Capsule Network based node embedding model to represent each task as a learnable feature vector; 2) a decoder: an attention-based model to facilitate a sequential output; and 3) context: that encodes the states of the mission and the robots. To train the CapAM model, the policy-gradient method based on REINFORCE is used. When evaluated over unseen scenarios, CapAM demonstrates better task completion performance and >10 times faster decision-making compared to standard non-learning based online MRTA methods. CapAM's advantage in generalizability, and scalability to test problems of size larger than those used in training, are also successfully demonstrated in comparison to a popular approach for learning to solve CO problems, namely the purely attention mechanism.