# DC-Ada: Reward-Only Decentralized Sensor Adaptation for Heterogeneous Multi-Robot Teams

arXiv: https://arxiv.org/abs/2604.03905 · HTML: https://mlsanity.com/paper/2604.03905/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 58 references that are in the map.
- First posted on arXiv 5 Apr 2026.

## Builds on (most cited first, 24 of 24)

- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [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)
- [QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation](https://mlsanity.com/paper/1806.10293/) (2018)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning](https://mlsanity.com/paper/2307.06135/) (2023)
- [Data-centric Artificial Intelligence: A Survey](https://mlsanity.com/paper/2303.10158/) (2023)
- [Optimal rates for zero-order convex optimization: the power of two function evaluations](https://mlsanity.com/paper/1312.2139/) (2013)
- [Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications](https://mlsanity.com/paper/1812.11794/) (2018)
- [A Survey of Multi-Agent Deep Reinforcement Learning with Communication](https://mlsanity.com/paper/2203.08975/) (2022)
- [Sim-to-Real Robot Learning from Pixels with Progressive Nets](https://mlsanity.com/paper/1610.04286/) (2016)
- [Heterogeneous-Agent Reinforcement Learning](https://mlsanity.com/paper/2304.09870/) (2023)
- [Self-Paced Deep Reinforcement Learning](https://mlsanity.com/paper/2004.11812/) (2020)
- [Heterogeneous Multi-Robot Reinforcement Learning](https://mlsanity.com/paper/2301.07137/) (2023)
- [Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation](https://mlsanity.com/paper/2403.08282/) (2024)
- [Kimera-Multi: a System for Distributed Multi-Robot Metric-Semantic Simultaneous Localization and Mapping](https://mlsanity.com/paper/2011.04087/) (2020)
- [Efficient Decentralized Visual Place Recognition From Full-Image Descriptors](https://mlsanity.com/paper/1705.10739/) (2017)
- [Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability](https://mlsanity.com/paper/2301.01649/) (2023)
- [Robust Task Scheduling for Heterogeneous Robot Teams under Capability Uncertainty](https://mlsanity.com/paper/2106.12111/) (2021)
- [SayCoNav: Utilizing Large Language Models for Adaptive Collaboration in Decentralized Multi-Robot Navigation](https://mlsanity.com/paper/2505.13729/) (2025)
- [Consensus-based Fast and Energy-Efficient Multi-Robot Task Allocation](https://mlsanity.com/paper/2209.10513/) (2022)
- [A Distributed Multi-Robot Framework for Exploration, Information Acquisition and Consensus](https://mlsanity.com/paper/2310.01930/) (2023)

## Abstract (arXiv)

Heterogeneity is a defining feature of deployed multi-robot teams: platforms often differ in sensing modalities, ranges, fields of view, and failure patterns. Controllers trained under nominal sensing can degrade sharply when deployed on robots with missing or mismatched sensors, even when the task and action interface are unchanged. We present DC-Ada, a reward-only decentralized adaptation method that keeps a pretrained shared policy frozen and instead adapts compact per-robot observation transforms to map heterogeneous sensing into a fixed inference interface. DC-Ada is gradient-free and communication-minimal: it uses budgeted accept/reject random search with short common-random-number rollouts under a strict step budget. We evaluate DC-Ada against four baselines in a deterministic 2D multi-robot simulator covering warehouse logistics, search and rescue, and collaborative mapping, across four heterogeneity regimes (H0--H3) and five seeds with a matched budget of 200,000 joint environment steps per run. Results show that heterogeneity can substantially degrade a frozen shared policy and that no single mitigation dominates across all tasks and metrics. Observation normalization is strongest for reward robustness in warehouse logistics and competitive in search and rescue, while the frozen shared policy is strongest for reward in collaborative mapping. DC-Ada offers a useful complementary operating point: it improves completion most clearly in severe coverage-based mapping while requiring only scalar team returns and no policy fine-tuning or persistent communication. These results position DC-Ada as a practical deploy-time adaptation method for heterogeneous teams.