ppo-seals-CartPole-v0
Educationreinforcement learning model by HumanCompatibleAI on Hugging Face (stable-baselines3). 187,490 downloads in the last 30 days as of 2026-10-15.
reinforcement learning model by nvidia on Hugging Face (onnx). 862 downloads in the last 30 days as of 2026-10-15.
Metatron-v1 is an open AI model published on Hugging Face by nvidia for reinforcement learning. Hugging Face reported 862 downloads in the 30 days to 2026-10-15. Weights are free to download from Hugging Face; licence terms are set by the publisher on the model card.
| Publisher | nvidia |
|---|---|
| Task | reinforcement learning |
| Library | onnx |
| Downloads (30 days) | 862 (as of 2026-10-15) |
| Price | Free to download (open weights) |
Listed as Free. Detailed prices haven't been checked from the official site yet; see Metatron-v1.
reinforcement learning model by HumanCompatibleAI on Hugging Face (stable-baselines3). 187,490 downloads in the last 30 days as of 2026-10-15.
reinforcement learning model by HumanCompatibleAI on Hugging Face (stable-baselines3). 45,036 downloads in the last 30 days as of 2026-10-15.
reinforcement learning model by helenlu94 on Hugging Face (stable-baselines3). 23,926 downloads in the last 30 days as of 2026-10-15.
reinforcement learning model by mradermacher on Hugging Face (transformers). 10,904 downloads in the last 30 days as of 2026-10-15.
reinforcement learning model by sb3 on Hugging Face (stable-baselines3). 8,777 downloads in the last 30 days as of 2026-10-15.
reinforcement learning model by mradermacher on Hugging Face (transformers). 7,353 downloads in the last 30 days as of 2026-10-15.
Metatron-v1 is an open AI model published on Hugging Face by nvidia for reinforcement learning. Hugging Face reported 862 downloads in the 30 days to 2026-10-15.
Metatron-v1 is listed as free.
1. Open the model card on Hugging Face for usage notes, the base model and the licence. 2. Load it with onnx (for Transformers: `pipeline("reinforcement-learning", model="nvidia/Metatron-v1")`). 3. Test it on a small sample of your own data before using it in production.
Related models include ppo-seals-CartPole-v0, ppo-Pendulum-v1, NoveltyAdapt-policies, Tifa-Deepsex-14b-CoT-GGUF, sac-BipedalWalkerHardcore-v3.
This page is generated from public listing data (source listing, tags, counts and our own link check); check the official page for features, licence and current pricing. Want to master tools like this? See the 100+ AI Tools Course.