Downloads · 30 days
0
pravsels/pi05-build-block-tower-rlt-6mix-retain-alpha05
pi05-build-block-tower-rlt-6mix-retain-alpha05 is a robotics model from pravsels. Use it for the robotics task on the model card, and read the license before you ship it in a product.
RL Token (RLT) encoder-decoder trained on the 6-dataset build-block-tower mixture, on top of the retain/step49999/alpha0.5 checkpoint from pi05-build-block-tower-6mix.
Downloads · 30 days
0
Access
Public
Updated Apr 17, 2026
Repo size
12.5 GB
Likes
0
Public
Click a slice to open those files.
Other12.5 GB · 100%
From the Hugging Face model README
RL Token (RLT) encoder-decoder trained on the 6-dataset build-block-tower mixture, on top of the retain/step_49999/alpha_0.5 checkpoint from pi05-build-block-tower-6mix.
This model is a lightweight transformer encoder-decoder which takes inputs from a frozen Pi-05 VLA backbone. The encoder compresses the VLA's final-layer prefix embeddings into a single RL token via a learned query. The decoder autoregressively reconstructs the original embeddings from only this token, forcing it to act as an information bottleneck. See Xu et al. (2026), Precise Manipulation with Efficient Online RL for the method.
This variant uses the retain/alpha_0.5 backbone — a checkpoint produced by applying representation-level retention (alpha=0.5 interpolation toward the pre-fine-tuning weights) to the 6mix baseline at step 49999.
pi05_rlt_build_block_tower_6mixpravsels/pi05-build-block-tower-6mix retain/step_49999/alpha_0.5 (frozen, rl_vla_loss_weight=0.0)| Step | Train Loss | Val Loss | Gap |
|---|---|---|---|
| 0 | — | 11354.7 | — |
| 1,000 | — | 2507.0 | — |
| 5,000 | 640.8 | 701.6 | 60.8 |
| 10,000 | 472.8 | 536.0 | 63.2 |
| 15,000 | 399.9 | 487.8 | 87.9 |
| 19,999 | 356.3 | 464.8 | 108.5 |
| 25,000 | 326.6 | 446.8 | 120.2 |
| 30,000 | 304.9 | 439.3 | 134.4 |
| 35,000 | 288.4 | 432.7 | 144.3 |
| 40,000 | 275.6 | 423.3 | 147.7 |
| 45,000 | 265.4 | 414.3 | 148.9 |
| 49,000 | 259.8 | 425.4 | 165.6 |
| 49,900 | 256.4 | — | — |
Val loss decreased steadily, reaching a minimum of 414.3 at step 45,000 before beginning to rise. The 45,000 checkpoint is recommended for deployment as it has the lowest validation loss.
| Step | Val Loss | Recommended | Params SHA256 |
|---|---|---|---|
| 19999 | 464.8 | 493ae11e5c95be5340e9106e54cac3f2219f6d1407a9081fc1c35595f5143cdb | |
| 45000 | 414.3 | ✓ | 1af50d87b765942801fd6be6afb5df3bcc69065636b614702f0b1f34fd3daec1 |
cd checkpoints/<step> && find params -type f | sort | xargs sha256sum | sha256sum
assets/ # Norm stats, valid indices, episode split
checkpoints/19999/params/ # Step 19999 model weights
checkpoints/45000/params/ # Step 45000 model weights (recommended)
TRAINING_LOG.md # Training log
Training curves: https://wandb.ai/pravsels/pi05-build-block-tower-rlt-6mix-retain-alpha05/runs/g5myo76p
import openpi.models.model as _model
import openpi.training.config as _config
config = _config.get_config(pi05_rlt_build_block_tower_6mix)
params = _model.restore_params(checkpoints/45000/params, restore_type=np.ndarray)
model = config.model.load(params)