[RAL 2026] Public code and model for ORION: Option-Regularized Deep Reinforcement Learning for Cooperative Multi-Agent Online Navigation.

🔹 ORION is an efficient RL planner for multi-agent navigation in partially known environments. It enables real-time, decentralized cooperation by coordinating individual target-reaching and team-level online uncertainty reduction via option-based networks and dual-stage navigation strategy.

We use conda/mamba to manage the environment.

conda create -n orion python=3.10 -y
conda activate orion

pip install torch torchvision
pip install opencv-python scikit-image imageio pandas
pip install matplotlib tensorboard
pip install ray wandb

Clone this repository and navigate to the directory.

git clone https://github.com/marmotlab/ORION-multi-agent-navigation.git
cd ORION-multi-agent-navigation

Training datasets are provided in:

• maps_priori/
• maps_GT/

Evaluation datasets are provided in:

• maps_priori_test_new_{n}/
• maps_GT_test_new_{n}/

where {n} denotes the number of agents in the team.

The training set consists of simple maps with 3 agents only.
During evaluation, ORION scales to larger teams (3, 4, 5, and 10 agents) and more complex environments without additional training.

We also provide a pretrained checkpoint. As ORION is a decentralized multi-agent navigation planner, the same checkpoint can be directly applied to different team sizes.

Examples of training (left) and evaluation (right) maps.

For training, configure the parameters in parameter.py, then run:

python driver.py

For evaluation, configure the parameters in test_parameter.py, then run:

python test_driver.py

Inline comments are provided in both files to facilitate parameter configuration.

We provide a ROS2-based deployment of ORION in the Multi-Robot-Development-Environment. This repository offers a multi-agent navigation and exploration framework, along with several simulation environments for development and evaluation.

If you find this work helpful, please consider citing:

@article{shizhe2026orion,
  title={ORION: Option-Regularized Deep Reinforcement Learning for Cooperative Multi-Agent Online Navigation},
  author={Shizhe, Zhang and Jingsong, Liang and Zhitao, Zhou and Shuhan, Ye and Yizhuo, Wang and Derek, Tan Ming Siang and Jimmy, Chiun and Yuhong, Cao and Guillaume, Sartoretti},
  journal={arXiv preprint arXiv:2601.01155},
  year={2026}
}

ORION is inspired by the following works, and we thank them for their contributions!

• Context-Aware Deep Reinforcement Learning for Autonomous Robotic Navigation in Unknown Area, CoRL 2023
• The Option-Critic Architecture, AAAI 2017
• ARiADNE ROS Planner, ICRA 2023/RA-L 2024
• CMU Development environment
• Octomap

Shizhe Zhang*, Jingsong Liang*, Zhitao Zhou, Shuhan Ye, Yizhuo Wang, Derek Ming Siang Tan, Jimmy Chiun, Yuhong Cao, Guillaume Sartoretti