# Capability-Aware Shared Hypernetworks for Flexible Heterogeneous Multi-Robot Coordination

arXiv: https://arxiv.org/abs/2501.06058 · HTML: https://mlsanity.com/paper/2501.06058/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 45 references that are in the map.
- First posted on arXiv 10 Jan 2025.

## Builds on (most cited first, 28 of 28)

- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [HyperNetworks](https://mlsanity.com/paper/1609.09106/) (2016)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [Efficient Online Reinforcement Learning with Offline Data](https://mlsanity.com/paper/2302.02948/) (2023)
- [Continual learning with hypernetworks](https://mlsanity.com/paper/1906.00695/) (2019)
- [Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks](https://mlsanity.com/paper/2006.07869/) (2020)
- [A Brief Review of Hypernetworks in Deep Learning](https://mlsanity.com/paper/2306.06955/) (2023)
- [Celebrating Diversity in Shared Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2106.02195/) (2021)
- [PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning](https://mlsanity.com/paper/1809.03531/) (2018)
- [Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharing](https://mlsanity.com/paper/2102.07475/) (2021)
- [Graph Neural Networks for Decentralized Multi-Robot Path Planning](https://mlsanity.com/paper/1912.06095/) (2019)
- [Simplifying Deep Temporal Difference Learning](https://mlsanity.com/paper/2407.04811/) (2024)
- [JaxMARL: Multi-Agent RL Environments and Algorithms in JAX](https://mlsanity.com/paper/2311.10090/) (2023)
- [Continual Model-Based Reinforcement Learning with Hypernetworks](https://mlsanity.com/paper/2009.11997/) (2020)
- [Hypernetworks in Meta-Reinforcement Learning](https://mlsanity.com/paper/2210.11348/) (2022)
- [Heterogeneous Multi-Robot Reinforcement Learning](https://mlsanity.com/paper/2301.07137/) (2023)
- [Recomposing the Reinforcement Learning Building Blocks with Hypernetworks](https://mlsanity.com/paper/2106.06842/) (2021)
- [Graph Policy Gradients for Large Scale Robot Control](https://mlsanity.com/paper/1907.03822/) (2019)
- [Hypernetworks for Zero-shot Transfer in Reinforcement Learning](https://mlsanity.com/paper/2211.15457/) (2022)
- [Recurrent Hypernetworks are Surprisingly Strong in Meta-RL](https://mlsanity.com/paper/2309.14970/) (2023)
- [System Neural Diversity: Measuring Behavioral Heterogeneity in Multi-Agent Learning](https://mlsanity.com/paper/2305.02128/) (2023)
- [Heterogeneous Multi-Agent Reinforcement Learning for Unknown Environment Mapping](https://mlsanity.com/paper/2010.02663/) (2020)
- [HyperMARL: Adaptive Hypernetworks for Multi-Agent RL](https://mlsanity.com/paper/2412.04233/) (2024)
- [MARBLER: An Open Platform for Standardized Evaluation of Multi-Robot Reinforcement Learning Algorithms](https://mlsanity.com/paper/2307.03891/) (2023)
- [Generalization of Heterogeneous Multi-Robot Policies via Awareness and Communication of Capabilities](https://mlsanity.com/paper/2401.13127/) (2024)

## Built on by (most cited first, 3 of 3)

- [JaxRobotarium: Training and Deploying Multi-Robot Policies in 10 Minutes](https://mlsanity.com/paper/2505.06771/) (2025)
- [Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2605.12388/) (2026)
- [Learning Adaptive Multi-Task Guidance, Navigation, and Control via Hypernetworks](https://mlsanity.com/paper/2607.24292/) (2026)

## Abstract (arXiv)

Recent advances have enabled heterogeneous multi-robot teams to learn complex and effective coordination skills. However, existing neural architectures that support heterogeneous teaming tend to force a trade-off between expressivity and efficiency. Shared-parameter designs prioritize sample efficiency by enabling a single network to be shared across all or a pre-specified subset of robots (via input augmentations), but tend to limit behavioral diversity. In contrast, recent designs employ a separate policy for each robot, enabling greater diversity and expressivity at the cost of efficiency and generalization. Our key insight is that such tradeoffs can be avoided by viewing these design choices as ends of a broad spectrum. Inspired by recent work in transfer and meta learning, and building on prior work in multi-robot task allocation, we propose Capability-Aware Shared Hypernetworks (CASH), a soft weight sharing architecture that uses hypernetworks to efficiently learn a flexible shared policy that dynamically adapts to each robot post-training. By explicitly encoding the impact of robot capabilities (e.g., speed and payload) on collective behavior, CASH enables zero-shot generalization to unseen robots or team compositions. Our experiments involve multiple heterogeneous tasks, three learning paradigms (imitation learning, value-based, and policy-gradient RL), and SOTA multi-robot simulation (JaxMARL) and hardware (Robotarium) platforms. Across all conditions, we find that CASH generates appropriately-diverse behaviors and consistently outperforms baseline architectures in terms of performance and sample efficiency during both training and zero-shot generalization, all with 60%-80% fewer learnable parameters.