Spaces:
Running on Zero
Apply for a GPU community grant: Academic project
This Space is an interactive demo for the paper "Representation over Routing: Learning Shared State Abstractions for Multi-Agent Reinforcement Learning" (arXiv: 2604.13517), which is now linked on the Hugging Face Papers page at https://huggingface.co/papers/2604.13517.
The demo visualizes Multi-Timescale PPO agents performing the "Intelligent Landing" task. Currently running on the free CPU tier, the rendering is slow and limits the educational value of the demo. A ZeroGPU grant would significantly improve the inference speed and provide a smoother, more accessible experience for the research community.
This is an academic project with openly released model weights on the Hugging Face Hub. The Space was created in response to an outreach from the Hugging Face open-source team (NielsRogge), who encouraged us to build this demo and mentioned the possibility of a ZeroGPU grant. We believe this demo serves strong educational and scientific dissemination purposes.
Hi @ben-dlwlrma , we've assigned ZeroGPU to this Space. Please check the compatibility and usage sections of the ZeroGPU documentation to make sure your Space runs correctly on ZeroGPU. If you're using a coding agent like Claude Code, you can also try Hugging Face's official huggingface-zerogpu skill, which guides the agent through ZeroGPU's constraints and migration steps.
If you're able to, please consider upgrading to Pro ($9/month) for a higher ZeroGPU quota plus features like Dev Mode and Private Storage.