S
SimpleVLA-RL
PRIME-RL/SimpleVLA-RL
[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
★1.8kstars
Python
MIT
Updated: Today
📋 Project at a Glance
Tap to expand
What's this?Models project leveraging reasoning and rl, built with Python, open-source
Who made it?Maintained by PRIME-RL team, 1.8K⭐ on GitHub, #725 out of 3201 in Models
Why does it exist?The PRIME-RL team recognized that existing reasoning tools in Models were hard to use. SimpleVLA-RL was designed to make rl more accessible.
What can it do?Key use cases: vla
How to install with AI?Use an AI coding assistant (Claude Code, Cursor, Copilot) to automatically set up pip dependencies and virtual env. Follow the README — the AI handles the rest.
🔗 github.com/PRIME-RL/SimpleVLA-RL | 官网 https://arxiv.org/abs/2509.09674
🔗 github.com/PRIME-RL/SimpleVLA-RL | 官网 https://arxiv.org/abs/2509.09674
Topics
reasoningrlvla