Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -44,3 +44,15 @@ Files here do not keep repo paths; point the loaders at them explicitly.
|
|
| 44 |
| Output-feedback scaling m=2/3/4, banks 1k/3k/8k | `round2/mimo_unstable/d2m{m}n{N}_*` | `data/round2/mimo_sof_scaling/` (banks, held-out sets, datasets, evaluated candidates) | `mimo_unstable_family.md` §D2 |
|
| 45 |
| Output-feedback scaling m=2..5, final full recipe (96k x 64, 3 seeds), banks 8k (+16k for m=4) | `round2/mimo_sof_scaling_full/d3f{m}{n}_{diff,reg}_s*_s96000.pth` | `data/round2/mimo_sof_scaling/` (`d3f_m*.json` results) | `mimo_unstable_family.md` §D3 |
|
| 46 |
| Furuta online re-synthesis on the unified F3 model (episode logs) | — | `data/round2/furuta_resynth_b2/` | `furuta_online_resynthesis.md` §B2 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
| Output-feedback scaling m=2/3/4, banks 1k/3k/8k | `round2/mimo_unstable/d2m{m}n{N}_*` | `data/round2/mimo_sof_scaling/` (banks, held-out sets, datasets, evaluated candidates) | `mimo_unstable_family.md` §D2 |
|
| 45 |
| Output-feedback scaling m=2..5, final full recipe (96k x 64, 3 seeds), banks 8k (+16k for m=4) | `round2/mimo_sof_scaling_full/d3f{m}{n}_{diff,reg}_s*_s96000.pth` | `data/round2/mimo_sof_scaling/` (`d3f_m*.json` results) | `mimo_unstable_family.md` §D3 |
|
| 46 |
| Furuta online re-synthesis on the unified F3 model (episode logs) | — | `data/round2/furuta_resynth_b2/` | `furuta_online_resynthesis.md` §B2 |
|
| 47 |
+
| SOF scaling, batch-256 equal-sample recipe (equivalence check for D3) | `round2/mimo_sof_scaling_b256/d3m*_s24000.pth` | `data/round2/mimo_sof_scaling/` | `mimo_unstable_family.md` §D3 |
|
| 48 |
+
|
| 49 |
+
## QUBE-Servo 2 hardware (2026-10-08): `models/round2/qube_*`, `data/round2/qube_*`
|
| 50 |
+
|
| 51 |
+
Fine-tuned on the measured lab unit (arm inertia, motor gain and cable spring identified on the rig; base JSON `qube_params_rig1.json`). Hardware report: `DiffusionControl/docs/qube_hardware_report.md`.
|
| 52 |
+
|
| 53 |
+
| model | what | hardware |
|
| 54 |
+
|---|---|---|
|
| 55 |
+
| `qube_rig1/rig1_s6000.pth` | F3 fine-tuned on a 2000-plant bank around the unit (mp, Lp +-10%) | 16/16 caught (computed TVLQR tracking) |
|
| 56 |
+
| `qube_rig1w/rig1w_s6000.pth` | same, mp and Lp +-30% (added-mass / other pendulum) | not yet run |
|
| 57 |
+
| `qube_rig1wg/rig1wg_s8000.pth` | fully generated controller: also outputs the TVLQR gain schedule K(t) (5-channel U-Net) | 6/6 caught |
|
| 58 |
+
| `qube_armprov/armprov_s6000.pth` | provisional (pre-sysid) arm, superseded | - |
|