Home › AI Agent / automation workflows › microduck-arena
Demo (Space)
microduck-arena
pollen-robotics/microduck-arena
Visit the microduck-arena website / project page →
What is microduck-arena
MicroDuck Arena is an open-source AI Agent evaluation arena released by Pollen Robotics. It supports multi-agent interaction, battles and benchmarking.
Key features
- Supports multi-agent strategies competing and being benchmarked on fixed tracks
- Strategies are evaluated on the server using five perturbation seeds and a specified speed range
- Supports both local execution and Hugging Face Space usage
- Published strategies can be downloaded and matches reproduced locally
- Provides training guides and rule documentation to help users submit their first strategy
Who it is for
Suitable for developers and researchers interested in robotics strategies, AI Agent evaluation or multi-agent competitions.
How to get started
- Visit https://huggingface.co/spaces/pollen-robotics/microduck-arena
- Read “Train your first policy” to learn the training method
- Open “Training & rules” to view the specific rules for the selected challenge
- Use uv run python scripts/deploy_space.py to deploy local changes to the Space
Compiled from public descriptions on the tool's official website / README / launch page. Pricing and user numbers have not been verified; please check the official website. Some sections were drafted with AI assistance. Written in Chinese and English; other languages are machine-translated.
Similar alternatives (AI Agent / automation workflows)
Get a “Featured on AI Hot List” badge · Submit a tool
← Back to “AI Agent / automation workflows” · Full hot list · Use-case lists