You can deploy this model and start earning money today!

haohw/
behavior-uncloning-baseline

Name: behavior-uncloning-baseline
Availability: InStock

safetensors

Views

No views yet

Behavior Uncloning - Baseline DiffusionPolicy

Baseline DiffusionPolicy trained on all LIBERO-10 episodes (379 episodes, ~101K frames).

Checkpoints

step_025000/ - 25K steps, 76% overall success rate
step_050000/ - 50K steps, 76% overall success rate (final)

Training Config

Model: DiffusionPolicy (267M params)
Dataset: HuggingFaceVLA/libero (LIBERO-10 subset)
Effective batch size: 64 x 8 GPUs = 512
Training time: ~20 hours on 8xA100-80GB
Framework: LeRobot v0.4.4

Per-Task Success Rates (step 50K)

T0	T1	T2	T3	T4	T5	T6	T7	T8	T9
10%	60%	80%	100%	80%	100%	60%	100%	70%	100%

Usage

python

from lerobot.policies.diffusion.modeling_diffusion import DiffusionPolicy
policy = DiffusionPolicy.from_pretrained("haohw/behavior-uncloning-baseline", subfolder="step_050000")

Project

Part of the behavior-uncloning project — machine unlearning for robot manipulation policies.