README.md

---
datasets:
- behavior-1k/2025-challenge-demos
- IliaLarchenko/behavior_224_rgb
license: apache-2.0
tags:
- robotics
pipeline_tag: robotics
---

This is an intermediate checkpoint that we used in our [1st place solution of the 2025 BEHAVIOR Challenge](https://github.com/IliaLarchenko/behavior-1k-solution).

This checkpoint is obtained by training the policy on 50 tasks simultaneously for ~2 weeks.

It is not part of our [final submission](https://huggingface.co/IliaLarchenko/behavior_submission). Also, we didn't run the whole evaluation of this checkpoint, but we would expect it to achieve a 15-20% q-score.

Paper: [Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge](https://huggingface.co/papers/2512.06951)
Project page: https://behavior.stanford.edu/challenge/
Code/GitHub Repository: [IliaLarchenko/behavior-1k-solution](https://github.com/IliaLarchenko/behavior-1k-solution)
arXiv: [2512.06951](https://arxiv.org/abs/2512.06951)

The [final submission checkpoints](https://huggingface.co/IliaLarchenko/behavior_submission)

## Sample Usage

This section provides a quick overview of how to get started with the model, adapted from the [GitHub repository](https://github.com/IliaLarchenko/behavior-1k-solution).

### Installation

```bash
# Clone with submodules (includes openpi and BEHAVIOR-1K)
git clone --recurse-submodules https://github.com/ilialarchenko/behavior-1k-solution.git
cd behavior-1k-solution

# Run setup script (installs uv, dependencies, and sets up environment)
bash setup_remote.sh
```

### Dataset Preparation

Download the official BEHAVIOR-1K dataset from HuggingFace:

```bash
# Login to HuggingFace (need to avoid request rate limit errors)
uv run huggingface-cli login

# Download the full dataset (~2TB)
uv run python - <<'PY'
from huggingface_hub import snapshot_download
snapshot_download(
  repo_id="behavior-1k/2025-challenge-demos",
  repo_type="dataset",
  local_dir="./data/behavior_dataset",
  local_dir_use_symlinks=False
)
PY
```

**Alternative**: Use the resized RGB-only dataset (224×224, ~260GB) for faster training:
```bash
uv run python - <<'PY'
from huggingface_hub import snapshot_download
snapshot_download(
  repo_id="IliaLarchenko/behavior_224_rgb",
  repo_type="dataset",
  local_dir="./data/behavior_224_rgb",
  local_dir_use_symlinks=False
)
PY
```

### Pre-training Setup

Compute dataset statistics and train FAST tokenizer:

```bash
# Compute normalization statistics with correlation matrix
uv run scripts/compute_norm_stats.py --config-name pi_behavior_b1k_fast --correlation

# Train FAST tokenizer for action discretization
uv run scripts/train_fast_tokenizer.py \
  --config-name pi_behavior_b1k_fast \
  --encoded-dims="0:6,7:23" \
  --vocab-size=1024
```

### Training

**Single GPU Training**:
```bash
uv run scripts/train.py pi_behavior_b1k_fast \
  --batch_size=16 \
  --num_train_steps=200000 \
  --save_interval=2000 \
  --keep_period=10000 \
  --log_interval=100
```

**Multi-GPU Training**:
```bash
uv run scripts/train.py pi_behavior_b1k_fast \
  --batch_size=2048 \
  --num_train_steps=200000 \
  --fsdp_devices=8 \
  --save_interval=250 \
  --keep_period=4000 \
  --log_interval=25
```

### Evaluation

Start the policy server:

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

In a separate terminal, [run evaluation](https://behavior.stanford.edu/challenge/baselines.html) (requires BEHAVIOR-1K environment):

```bash
python BEHAVIOR-1K/omnigibson/learning/eval.py \
  log_path=./eval_logs \
  policy=websocket \
  task.name=make_microwave_popcorn \
  model.host=localhost \
  eval_instance_ids="[0,1,2,3]"
```

## Citation

If you find this work useful, please cite:

```bibtex
@misc{larchenko2025behavior,
      title={Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge}, 
      author={Ilia Larchenko and Gleb Zarin and Akash Karnatak},
      year={2025},
      eprint={2512.06951},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2512.06951}, 
}
```