ACT-so101-pickplace-sim-2500-v1.0

Completed ACT policy trained on caspar/so101_pickplace_sim for 2,500 optimizer steps. Published 2026-11-13. Local completed paired ACT comparison; final checkpoint, without test-driven checkpoint selection.

This is a native LeRobot 0.6.1 policy package, including the original model weights, policy configuration, preprocessor/postprocessor definitions and normalization tensors. It predicts 6-dimensional joint actions from 6-dimensional state and top/wrist RGB cameras (3 x 240 x 320), with action chunk size 50. Camera names and normalization must match the saved configuration. Architecture: ACT with a ResNet18 backbone initialized from ImageNet weights, Transformer encoder/decoder and CVAE.

Loading

Install lerobot==0.6.1 in a compatible environment. Download a pinned snapshot with hf download caspar/ACT-so101-pickplace-sim-2500-v1.0 --revision v1.0 --local-dir ./policy, then load it with ACTPolicy.from_pretrained("./policy") from lerobot.policies.act.modeling_act. Use LeRobot's policy pre/postprocessors from that same directory for observation normalization and conversion of predicted actions to joint units. Loading the neural network alone does not apply those processors. Training/evaluation scripts and simulator are in physicalai_tutorial.

Evidence and limits

See training_summary.json and evaluation.json for original run settings and historical simulation results. Publication verified original checkpoint SHA256, processor assets, and finite tensors. No new training, policy inference or simulator rollout was run for this upload. Historical simulation success rates are not real-robot validation; keep them tied to the recorded seeds and success criterion. The _150 dataset name does not mean 150 retained episodes: that dataset contains 117 episodes; the basic dataset contains 43 episodes. The 10K checkpoint is a separate run from the 2500-step comparison. No optimizer states, source demonstrations or credentials are included.