CTR Diffusion Policy Pick Dual Bottles — Right-first
This public inference checkpoint is the verified final checkpoint from CTR training Experiment E355, which is linked from the core experiment data table.
- Architecture: Diffusion Policy
- Task: RoboTwin Pick Dual Bottles
- Training variant: Right-first
- Final optimizer update: 71686
- Dataset: Shiki42/ctr-pick-dual-bottles-right-first-20260916
- Dataset revision: de31195100138e4fa32c9b1e10ae92f9da77a948
- Source Experiment: E355
No IdleMask. LeRobot Diffusion Policy with observation horizon 2, prediction horizon 16, execution horizon 8 and DDPM100 inference.
The repository contains inference parameters, processors/assets, resolved configuration, and a generated SHA256SUMS manifest. Optimizer state, data-loader state, logs, credentials, and training caches are intentionally excluded.
Results remain governed by the source Experiment and its separate evaluation Experiments. Publication does not upgrade a reported or audit-pending result to archived/confirmed.
- Downloads last month
- 21