Behavior Uncloning — KL (step 20)

VLA unlearning checkpoint: pi0.5 model with KL unlearning applied.

Results

Metric Value
Method KL
Training Steps 20
Forget Task "turn on the stove" (LIBERO-Goal T6)
Forget SR 40% (baseline: 100%)
Retain SR 95.6% (baseline: 97.8%)
HM 0.81

Usage

# Serve with openpi
uv run scripts/serve_policy.py --env LIBERO policy:checkpoint \
    --policy.config pi05_libero --policy.dir <path_to_checkpoint>

Method

KL Minimization: L = -L_forget + γ·L_retain + γ·||L_cur - L_orig||². Anchors retain behavior to original model.

Base model: pi0.5 LIBERO

See full report: experiment_report.md

Downloads last month

-

Downloads are not tracked for this model. How to track
Video Preview
loading