# Automated Generation of Diverse Courses of Actions for Multi-Agent Operations using Binary Optimization and Graph Learning

arXiv: https://arxiv.org/abs/2506.20031 · HTML: https://mlsanity.com/paper/2506.20031/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 24 references that are in the map.
- First posted on arXiv 24 Jun 2025.

## Builds on (most cited first, 6 of 6)

- [Graph Capsule Convolutional Neural Networks](https://mlsanity.com/paper/1805.08090/) (2018)
- [Learning Scalable Policies over Graphs for Multi-Robot Task Allocation using Capsule Attention Networks](https://mlsanity.com/paper/2205.03321/) (2022)
- [Efficient Planning of Multi-Robot Collective Transport using Graph Reinforcement Learning with Higher Order Topological Abstraction](https://mlsanity.com/paper/2303.08933/) (2023)
- [Decentralized Task Allocation in Multi-Robot Systems via Bipartite Graph Matching Augmented with Fuzzy Clustering](https://mlsanity.com/paper/1807.07957/) (2018)
- [Diversifying Agent's Behaviors in Interactive Decision Models](https://mlsanity.com/paper/2203.03068/) (2022)
- [A Graph-based Adversarial Imitation Learning Framework for Reliable & Realtime Fleet Scheduling in Urban Air Mobility](https://mlsanity.com/paper/2407.12113/) (2024)

## Abstract (arXiv)

Operations in disaster response, search & rescue, and military missions that involve multiple agents demand automated processes to support the planning of the courses of action (COA). Moreover, traverse-affecting changes in the environment (rain, snow, blockades, etc.) may impact the expected performance of a COA, making it desirable to have a pool of COAs that are diverse in task distributions across agents. Further, variations in agent capabilities, which could be human crews and/or autonomous systems, present practical opportunities and computational challenges to the planning process. This paper presents a new theoretical formulation and computational framework to generate such diverse pools of COAs for operations with soft variations in agent-task compatibility. Key to the problem formulation is a graph abstraction of the task space and the pool of COAs itself to quantify its diversity. Formulating the COAs as a centralized multi-robot task allocation problem, a genetic algorithm is used for (order-ignoring) allocations of tasks to each agent that jointly maximize diversity within the COA pool and overall compatibility of the agent-task mappings. A graph neural network is trained using a policy gradient approach to then perform single agent task sequencing in each COA, which maximizes completion rates adaptive to task features. Our tests of the COA generation process in a simulated environment demonstrate significant performance gain over a random walk baseline, small optimality gap in task sequencing, and execution time of about 50 minutes to plan up to 20 COAs for 5 agent/100 task operations.