doug-act-stack-80k / README.md
dmcdono7's picture
Upload policy weights
5050e39 verified
|
Raw History Blame Contribute Delete
878 Bytes
metadata
tags:
  - LeRobot
  - ACT
  - so101
  - robotics
datasets:
  - hrl-imerse/doug-stack-98-trimmed

ACT block stacking, 80k steps (SO-101, wrist camera)

ACT (chunk_size 100, batch 8), trained on hrl-imerse/doug-stack-98-trimmed for 170k steps (88 train / 10 val episodes). This is the 80k checkpoint.

  • Augmentation: colour jitter plus RandomAffine (±5°, ±5% shift).
  • Validation loss plateaued at about 0.57 after 10k steps.

Real-arm tests (2026-11-17, temporal ensembling coeff 0.01, one trial each):

Checkpoint Result
80k placed orange perfectly, then missed green; the best of 20k/60k/80k/100k/170k
20k, 60k, 100k, 170k 0 blocks
  • Exec 15 was jerky and much worse than ensembling.
  • Grasps often missed by about 0.5 in on either side.

Run with lerobot-rollout ... --policy.n_action_steps=1 --policy.temporal_ensemble_coeff=0.01.