---
license: apache-2.0
library_name: openpi
pipeline_tag: robotics
tags:
  - behavior-1k
  - vision-language-action
  - pi0.5
  - robot-learning
  - flow-matching
  - jax
---

# pi05-rft-behavior1k

A **Pi0.5 vision-language-action policy** adapted for **long-horizon BEHAVIOR-1K
household manipulation** (2025 BEHAVIOR Challenge, NeurIPS 2025).

This checkpoint is the `ft_ckpt2` model (training step **9999**), a task-specialised
fine-tune used for the **picking_up_trash, picking_up_toys, tidying_bedroom,
collecting_childrens_toys** tasks (task IDs **1 / 7 / 18 / 21**).

- 📦 **Code & full pipeline:** <https://github.com/Sunliu36/Behavior1kChallenge_Solution_by_SHAWN>
- 🧪 **Sibling method (point-cloud SFT):** <https://github.com/Sunliu36/Behavior1KChallenge_minor_Solution_by_SHAWN>

## What it is

An [orbax](https://github.com/google/orbax) checkpoint with `params/` + `assets/`
(per-timestamp normalisation stats), directly loadable by the policy server in the
project repo:

```bash
uv run scripts/serve_b1k.py policy:checkpoint \
    --policy.config pi_behavior_b1k_fast \
    --policy.dir <path-to-this-checkpoint>
```

The optimizer state (`train_state/`) is intentionally **not** included — only the
inference-ready weights and normalisation assets are published.

## Fine-tuning data

This checkpoint was produced by **continuing training from the base Pi0.5
checkpoint** (`checkpoint_2`) on **human teleoperation demonstrations** drawn from the
[`IliaLarchenko/behavior_224_rgb`](https://huggingface.co/datasets/IliaLarchenko/behavior_224_rgb)
LeRobot dataset, filtered to the four target tasks (head camera, 224×224 RGB):

| Task ID | Task                       | Episodes | Frames        | ≈ Hours @30 fps |
|--------:|----------------------------|---------:|--------------:|----------------:|
| 1       | picking_up_trash           | 200      | 1,053,550     | 9.8             |
| 7       | picking_up_toys            | 200      | 3,778,110     | 35.0            |
| 18      | tidying_bedroom            | 200      | 2,207,489     | 20.4            |
| 21      | collecting_childrens_toys  | 200      | 3,837,265     | 35.5            |
| **Total** |                          | **800**  | **10,876,414**| **≈ 100.7**     |

So the fine-tune used **800 demonstration episodes (200 per task)** — roughly
**10.9 M frames / ~100 hours** of teleoperation at 30 fps, **head camera only**.

> Note: this particular checkpoint is a *supervised* fine-tune on human
> demonstrations. The broader project also explores rejection-sampling fine-tuning
> (RFT) with pose-perturbed rollouts — see the GitHub repo for that pipeline.

## Training setup

| Setting | Value |
|---|---|
| Backbone | Pi0.5 (PaliGemma VLM + flow-matching action expert), task embeddings (no text) |
| Init from | base `checkpoint_2` params |
| Frozen | PaliGemma LLM backbone + vision backbone (only action-specific params train) |
| Steps | 10,000 (this checkpoint = step 9999) |
| Batch size | 8 |
| Optimizer | cosine decay, warmup 200, peak LR 5e-5 → 5e-6 |
| Action space | Δ-joint, 30-step horizon, 32-dim |
| Aux losses | FAST tokens (0.05), subtask/stage prediction (0.1), correlation-aware flow noise (β=0.5) |
| Camera | head (224×224 RGB) |

## Attribution

Built on the open-source **Pi0.5** backbone (Physical Intelligence) and the
**Robot Learning Collective / IliaLarchenko** BEHAVIOR-1K solution, with
post-training ideas from the **Comet** report. Full credit and references in the
[project README](https://github.com/Sunliu36/Behavior1kChallenge_Solution_by_SHAWN#acknowledgments-and-references).

## Citation

```bibtex
@techreport{liu2026behavior1k_rft,
  author      = {Shao-Yang Liu},
  title       = {Adapting Vision-Language-Action Models for BEHAVIOR-1K Household Tasks},
  institution = {National Tsing Hua University},
  year        = {2026},
  email       = {shawnliu@gapp.nthu.edu.tw}
}
```