# Curriculum Imitation Learning of Distributed Multi-Robot Policies

arXiv: https://arxiv.org/abs/2509.25097 · HTML: https://mlsanity.com/paper/2509.25097/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 29 Sep 2025.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 14 of 14)

- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [An Algorithmic Perspective on Imitation Learning](https://mlsanity.com/paper/1811.06711/) (2018)
- [Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey](https://mlsanity.com/paper/2003.04960/) (2020)
- [Reverse Curriculum Generation for Reinforcement Learning](https://mlsanity.com/paper/1707.05300/) (2017)
- [VMAS: A Vectorized Multi-Agent Simulator for Collective Robot Learning](https://mlsanity.com/paper/2207.03530/) (2022)
- [Multi-Agent Imitation Learning for Driving Simulation](https://mlsanity.com/paper/1803.01044/) (2018)
- [BenchMARL: Benchmarking Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2312.01472/) (2023)
- [CM3: Cooperative Multi-goal Multi-stage Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1809.05188/) (2018)
- [Variational Automatic Curriculum Learning for Sparse-Reward Cooperative Multi-Agent Problems](https://mlsanity.com/paper/2111.04613/) (2021)
- [Decentralized Multi-Agent Pursuit using Deep Reinforcement Learning](https://mlsanity.com/paper/2010.08193/) (2020)
- [Imitation Learning by State-Only Distribution Matching](https://mlsanity.com/paper/2202.04332/) (2022)
- [Large Scale Distributed Collaborative Unlabeled Motion Planning with Graph Policy Gradients](https://mlsanity.com/paper/2102.06284/) (2021)
- [LEMURS: Learning Distributed Multi-Robot Interactions](https://mlsanity.com/paper/2209.09702/) (2022)
- [Learning Multi-Objective Curricula for Robotic Policy Learning](https://mlsanity.com/paper/2110.03032/) (2021)

## Built on by (most cited first, 1 of 1)

- [EmboTeam: Grounding LLM Reasoning into Reactive Behavior Trees via PDDL for Embodied Multi-Robot Collaboration](https://mlsanity.com/paper/2601.11063/) (2026)

## Abstract (arXiv)

Learning control policies for multi-robot systems (MRS) remains a major challenge due to long-term coordination and the difficulty of obtaining realistic training data. In this work, we address both limitations within an imitation learning framework. First, we shift the typical role of Curriculum Learning in MRS, from scalability with the number of robots, to focus on improving long-term coordination. We propose a curriculum strategy that gradually increases the length of expert trajectories during training, stabilizing learning and enhancing the accuracy of long-term behaviors. Second, we introduce a method to approximate the egocentric perception of each robot using only third-person global state demonstrations. Our approach transforms idealized trajectories into locally available observations by filtering neighbors, converting reference frames, and simulating onboard sensor variability. Both contributions are integrated into a physics-informed technique to produce scalable, distributed policies from observations. We conduct experiments across two tasks with varying team sizes and noise levels. Results show that our curriculum improves long-term accuracy, while our perceptual estimation method yields policies that are robust to realistic uncertainty. Together, these strategies enable the learning of robust, distributed controllers from global demonstrations, even in the absence of expert actions or onboard measurements.