Upload folder using huggingface_hub

closed-loop-checkpoints/README.md

@@ -0,0 +1,20 @@
+# closed-loop-checkpoints — policies + tactile tokenizer (T-Rex reproduction sim study)
+
+Checkpoints from the closed-loop Isaac Sim study in
+https://github.com/physercoe/trex-repro (`docs/CLOSED_LOOP_EVAL.md`).
+Task: press-in peg-in-hole, RH56 hand, Isaac Sim 5.1 / IsaacLab 2.3.2,
+tactile = ground-truth F6 wrenches. PyTorch `.pt` state dicts; architectures
+in `closed_loop/bc_policy.py` / `train_ppo.py` / `train_vqvae.py`.
+
+| file | role | eval SR (σ=20 mm clean / +disturbance) |
+|---|---|---|
+| `ppo3_champion_model_iter800_eval0973.pt` | blind PPO base ("champion", variant (b)); SR 0.973 on the clean task | 0.586 / 0.629 (frozen) |
+| `ppo4_blind_model_final.pt` | blind fine-tune control (b′) | 0.785 / 0.766 |
+| `ppo4_raw_model_0.pt` | raw-F6 tactile variant (c), ~iter 340 | 0.789 / 0.734 |
+| `ppo4_tac2_model_final.pt` | VQ-token tactile variant (a) | 0.754 / 0.746 |
+| `vqvae4_sim_tactile_vqvae.pt` + `vqvae4_norm_stats.npz` | tactile VQ-VAE tokenizer (30 Hz 16-step F6 windows → one-hot codes) + normalization stats | — |
+
+All fine-tunes used identical PPO budget (400 iters, 512 envs) from the
+champion. Verdict of the study: tactile VQ-token features gave no robust
+advantage over the same-budget blind control in this setup — see the repo for
+the full table and caveats. License: MIT.

closed-loop-checkpoints/ppo3_champion_model_iter800_eval0973.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b7098a3c1f934fe12766945fafc262e9bc6ffdf27f173a00d2abbe5c1a880e
+size 15460567

closed-loop-checkpoints/ppo4_blind_model_final.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a6a2916dca1b7223318949be17485d5b1b36018cc5a8fe24de37add64a41f2
+size 15461311

closed-loop-checkpoints/ppo4_raw_model_0.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f67a6d49320c55e73093f125832b7cccfd755a5a33b6f256d2080b6d55824d3
+size 15829207

closed-loop-checkpoints/ppo4_tac2_model_final.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3cffd18c9e5f0eee9e033491408c7147217a57d7f2c9b04e417bed53a062fe
+size 19393471

closed-loop-checkpoints/vqvae4_norm_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:033e5c1707849afb6cd28fa9b5201f129c81f20d4a6a418569b4a63d85fa6a8a
+size 508

closed-loop-checkpoints/vqvae4_sim_tactile_vqvae.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc9c84e1b4c011da97e2288bd024ed2612ea367702087ec663f4bf6acf05dbdf
+size 3733439