You can deploy this model and start earning money today!

haohw/
behavior-uncloning-po-step60

Views

No views yet

Behavior Uncloning — PO (step 60)

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

Metric	Value
Method	PO
Training Steps	60
Forget Task	"turn on the stove" (LIBERO-Goal T6)
Forget SR	0% (baseline: 100%)
Retain SR	100.0% (baseline: 97.8%)
HM	1.0

bash

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

Action Redirection (PO): L = L_flow(obs_forget, 0) + β·L_retain. Trains model to output zero actions on forget task.