nosuke113/pi0.5-libero-plus-lora

pi0.5 LIBERO-plus LoRA

LoRA fine-tuned weights of pi0.5 (PaliGemma-2B + Action Expert 300M) on the LIBERO-plus dataset, targeting the Action Expert and projection layers.

---

1. Model Configuration

Item	Value
Base Model	lerobot/pi05_libero_base (commit a217bfd)
This Repo	nosuke113/pi0.5-libero-plus-lora (commit db2ccc2)

---

2. Training

Dataset

The model was trained on nosuke113/libero-plus-deduplicated, which is a deduplicated version of the original lerobot/libero_plus dataset.

Data Split Methodology

The validation set was carefully constructed to prevent data leakage. Since the original dataset contains identical physical trajectories artificially augmented with different visual appearances, a simple random split would result in the model evaluating on physical trajectories it has already seen during training, leading to an artificially low validation loss.

To address this, we computed a SHA-1 hash over the full action sequence of each episode. Episodes sharing the same action hash (i.e., identical physical trajectories) were grouped together. The train/val split was then performed at the trajectory level, ensuring that all episodes belonging to a specific physical trajectory are placed entirely in either the training set or the validation set.

This strict trajectory-level separation means the model's validation loss accurately reflects its ability to generalize to unseen physical demonstrations, rather than just memorizing seen trajectories with different textures or lighting.

Training Details

Item	Value
Dataset	nosuke113/libero-plus-deduplicated (deduplicated: 8,395 episodes / 1,681 trajectories)
Data Split	Trajectory-level held-out (train: 1,376 traj / 6,873 ep, val: 154 traj / 767 ep, overlap: 0)
Fine-tuning	LoRA (Rank = 16, Alpha = 32, Action Expert + Projection Layers)
Checkpoint Path	checkpoints/libero_plus_b8_r16_step35000 (b8: batch_size=8, r16: LoRA rank=16)
Steps	35,000
Optimizer	AdamW (lr=1e-4, batch_size=8, Cosine Scheduler)
Code	takashinnosuke/parc2026-submission-code (commit abdba5b)

---

3. Evaluation Dataset & Perturbation Axes

The evaluation dataset containing the 180 held-out tasks is available at nosuke113/libero-plus-evaluation. These tasks are constructed along 4 perturbation axes from the LIBERO-plus BDDL scene definitions.

1. Base — Standard BDDL scenes. Camera (0, 0, 100, 0, 0), fixed object poses, no noise.
2. View — Camera orbit angle (0-356 deg), zoom distance (100-191), and gaze tilt are varied.
3. Noise — Image corruptions: Gaussian noise, motion blur, fog, glass distortion (level 8-48).
4. Moved — Object initial positions shifted by several cm from default.

---

4. Evaluation Results (900 Rollouts)

Measured on 180 fully held-out tasks with n=5 seeds (900 total rollouts). Closed-loop control with max 600 steps per episode, bfloat16 mixed precision on NVIDIA L4 GPU. Inference used Receding Horizon Control (RTC) with an action chunk size of 5. Note: The evaluation results below were measured using the checkpoint at 35,000 steps.

Metric	Value	Note
Total Episodes	900	180 tasks x 5 seeds
Overall Success Rate	46.00% (414/900)	95% Wilson CI: [42.7%, 49.3%]
Collision Rate	32.00% (288/900)	1mm displacement / link collision
Avg Steps	362.9	Max 600 steps
Action Jerk	0.0221	Mean step-to-step 6-DoF delta

Breakdown by Perturbation

Category	N	Success Rate	Collision Rate	Avg Steps
Base	150	78.67% (118/150)	15.33%	247.9
View	300	55.00% (165/300)	32.67%	286.6
Noise	300	30.67% (92/300)	29.33%	441.0
Moved	150	26.00% (39/150)	52.67%	474.2

Robustness across Perturbations

Parallel playback comparing Base, View, Noise, and Position perturbed evaluation environments.

Task: Put the black bowl on the plate	Task: Turn on the stove bottom
Task: Put the black bowl in the top drawer

---

5. Quickstart

This model is fully compatible with the Hugging Face lerobot library. You can instantiate it with a few lines of code:

from lerobot.common.policies.factory import make_policy

# Load the policy with LoRA weights
policy = make_policy(repo_id="nosuke113/pi0.5-libero-plus-lora")
policy.eval()

# Example usage (assuming `obs` is provided by the environment)
# obs = {
#     "observation.images.agentview": ...,
#     "observation.images.robot0_eye_in_hand": ...,
#     "observation.state": ...,
# }
# action = policy.select_action(obs)

---

6. License & Attribution

Component	License
Model weights (LoRA)	Google Gemma Terms of Use
This repository (Code)	MIT
Base model (lerobot/pi05_libero_base)	Google Gemma Terms of Use
lerobot library	Apache License 2.0
libero package	MIT License
Training data (lerobot/libero_plus)	MIT License (Inherited from original LIBERO repository)