tduggan93/pi0-hanoi-end-to-end

PI0 Hanoi End-to-End Checkpoint (30k steps)

This is a checkpoint for the pi0 (Physical Intelligence) model trained on the Hanoi task.

Model Details

• Task: Hanoi Tower puzzle
• Training Steps: 30,000
• Model Type: End-to-end policy
• Framework: JAX/Flax
• Dataset: hanoi_300_lerobot

Checkpoint Structure

• params/: Model parameters
• train_state/: Training state
• assets/: Additional assets including normalization statistics
• _CHECKPOINT_METADATA: Checkpoint metadata

Usage

This checkpoint can be loaded using the appropriate JAX/Flax model loading utilities in your training pipeline.

Training Configuration

• Dataset: hanoi_300_lerobot
• Fine-tuning step: ft1
• Total training steps: 30,000

Model Card

This model is trained for the Hanoi Tower puzzle task using end-to-end policy learning. The model takes visual observations and outputs actions for robotic manipulation.

Limitations

• Trained specifically on Hanoi Tower puzzle
• Performance may vary on different manipulation tasks