Upload README.md with huggingface_hub

README.md

@@ -25,7 +25,11 @@ carry and presents the policy with the same commands and stage flag it trained
 under. The observation and action layouts are frozen in `interface.py`; running
 the network under any other layout produces garbage rather than an error.
 Pinned stack: Isaac Sim 5.1.0, Isaac Lab v2.3.2, rsl_rl 3.1.2, torch 2.7.0+cu128
-(see `configs/versions.lock` in the repository).
+(see `configs/versions.lock` in the repository). Scope: simulated whole-body
+loco-manipulation with a hybrid PPO + state-machine controller; basket pose is
+read from the simulator with synthetic noise — vision-based perception and
+sim-to-real transfer are out of scope. SHA-256 hashes of these files are in the
+repository's `results/manifest.json`.
 
 ## Files
 
@@ -52,16 +56,18 @@ from bank states.
 
 ## Results (`chain.pt` with the repository's commander)
 
-All numbers use this one checkpoint (training seed 42), three evaluation
-seeds, 500 episodes each. Strict full-chain success requires reaching the
+All numbers use this one checkpoint (training seed 42); the baseline uses
+three evaluation seeds of 500 episodes each; the 15 s, held-out and
+training-conditions checks use one seed each. Strict full-chain success requires reaching the
 carry phase, keeping the elevated basket to episode timeout, and moving it at
 least 1.0 m after the carry begins.
 
 - Strict, 10 s episodes (the training horizon): **1,216 of 1,500 — 81.1 %**
   (95 % Wilson CI 79.0–83.0 %; per-seed 80.8 / 81.0 / 81.4 %). The shortfall
   against the softer metric is the episode clock: carry distances have a median
-  of 1.4 m with no mass near zero, and with 15 s episodes on the same spawns
-  strict success is **99.4 %** (median carry distance 3.2 m).
+  of 1.4 m (10th percentile 0.87 m), and with 15 s episodes on the same spawn
+  distribution (one evaluation seed, 500 episodes) strict success is **99.4 %**
+  (median carry distance 3.2 m).
 - Reached the carry phase and retained the elevated basket through timeout (no
   distance requirement): 1,476 of 1,500 — 98.4 % (97.6–98.9 %; per-seed
   98.4 / 97.8 / 99.0 %).
@@ -70,9 +76,12 @@ We observed zero falls, zero basket knock-away events, and three transient
 retention-latch loss events (0.002 per episode); an episode can re-establish
 retention after a latch loss.
 
-| | Walk | Carry | Lift | Thread | **Full chain** |
+Per-stage evaluation — reached-phase/retention metrics, no carry-distance
+requirement (strict full-chain numbers are above):
+
+| | Walk | Carry | Lift | Thread | Full chain (reached-carry) |
 |---|---|---|---|---|---|
-| Success | 98.7 % | 95.9 % | 98.9 % | 82.2 % | **98.4 %** |
+| Success | 98.9 % | 95.9 % | 98.9 % | 82.2 % | 98.4 % |
 
 Robustness (one policy, no retraining): mean success per tested handle opening
 stayed at or above 95.5 % across 15–35 cm (lowest single evaluation seed:
@@ -90,7 +99,8 @@ over 500 episodes.
 Things the numbers do not show: the 3 seeds are evaluation seeds of one trained
 policy (retraining variance was not measured); the evaluation environment turns
 off Isaac Lab's proprioceptive noise and pushes (under full training conditions
-the chain scores 100 % / 500 episodes); the state machine's constants were tuned
+the chain scores 87.6 % strict / 100 % reached-carry over 500 episodes, one
+evaluation seed); the state machine's constants were tuned
 on the training spawn distribution. The repository README has the full
 discussion, sweep plots, and ablations.