pi05 SO-101 green-cube policy (vla-agent-loop)
Produced by one iteration of vla-agent-loop: rollouts collected on the physical SO-101 rig, merged with the base teleop dataset, scored for progress by Robometer-4B (top camera), then finetuned on HPC with RA-BC sample weighting.
| Base policy | k1000dai/pi05_so101_pick_up_and_place_on_the_orange_sheet_70_base |
| Training dataset | k1000dai/pick-up-green-cube-and-place-on-the-right-side-o-20260725-145638-iter2-merged (124 episodes) |
| Steps / batch size | 10000 / 8 |
| Sample weighting | rabc (kappa=0.01, head_mode=sparse) |
| Task prompt | pick_up_green_cube_and_place_on_the_right_side_of_the_orange_sheet |
Evaluation
Not evaluated: the rig's evaluation dataflow hung when the arm's serial link dropped, and the run was stopped before it could be re-run.
Note that the rig's on-policy success rate is measured over very few episodes; treat any single evaluation here as an estimate with a wide confidence interval.