Skip to content

Updating RL results #146

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
WilliamYue37 merged 3 commits into from
Mar 17, 2026
Merged

Updating RL results #146

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
7a88714
Updating RL results
akshay18iitg Mar 17, 2026
08d356a
Updating RL results
akshay18iitg Mar 17, 2026
2c32adf
Updating RL results
akshay18iitg Mar 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ OpenTau ($\tau$) is a tool developed by *[Tensor][1]* to bridge this gap, and we
| Simulation Environments for Evaluating Models | ❌ | ✅ | ✅ |
| Create Validation Splits During Training | ❌ | ❌ | ✅ |
| $\pi^{*}_{0.6}$ style Reinforcement Learning Pipeline | ❌ | ❌ | ✅ |
| Post-training on Human Data (Beta)| ❌ | ❌ | ✅ |
| Post-training on Human Data| ❌ | ❌ | ✅ |
| Framework | Jax / PyTorch | PyTorch | PyTorch |

## Quick Start
Expand All @@ -64,6 +64,7 @@ We provide fully functioning $\pi_{0.5}$ checkpoints trained with high success r

| Model Checkpoint | Description | Success Rate (%) |
|-------------------------------|---------------------------------------------------------------------------------------------------------------|--------------------------------------------------------------------|
| [TensorAuto/moka_pot_libero_sft][6] <br> [TensorAuto/moka_pot_RECAP_R0][7] <br> [TensorAuto/moka_pot_RECAP_R1][8] | A $\pi_{0}$ RECAP model checkpoint trained on moka pot task on libero. | 83% <br> 89% <br> 90% |
| [TensorAuto/tPi0.5-libero][2] | A $\pi_{0.5}$ model checkpoint trained on the LIBERO dataset with discrete actions and knowledge insulation. | 98.4% (10) <br> 97.6% (Goal) <br> 100% (Object) <br> 98% (Spatial) |
| [TensorAuto/pi05_base][5] | A $\pi_{0.5}$ model checkpoint converted from the official openpi checkpoint, with language embeddings added. | N/A |
| More coming soon... | | |
Expand All @@ -77,3 +78,6 @@ This project builds on the $\pi$ series of [papers][3] and many other open-sourc
[3]: https://www.pi.website/blog
[4]: https://huggingface.co/lerobot
[5]: https://huggingface.co/TensorAuto/pi05_base
[6]: https://huggingface.co/TensorAuto/moka_pot_libero_sft
[7]: https://huggingface.co/TensorAuto/moka_pot_RECAP_R0
[8]: https://huggingface.co/TensorAuto/moka_pot_RECAP_R1
Loading