Upload README.md with huggingface_hub

README.md

@@ -13,7 +13,7 @@ tags:
 
 # HAMPER — G1 basket pickup policy
 
-Pretrained weights for [HAMPER](https://github.com/<your-github-username>/HAMPER):
+Pretrained weights for [HAMPER](https://github.com/WilliamHangXu/HAMPER):
 a Unitree G1 humanoid that walks up to a basket on the floor, threads its
 forearm through the handle, lifts it, and carries it away. Trained with PPO
 (rsl_rl) in Isaac Lab through a staged curriculum, on a single RTX A6000.
@@ -29,16 +29,21 @@ Pinned stack: Isaac Sim 5.1.0, Isaac Lab v2.3.2, rsl_rl 3.1.2, torch 2.7.0+cu128
 
 ## Files
 
-| File | What it is | Trained iterations |
-|---|---|---|
-| `chain.pt` | **The final policy** — the full task | 9,496 total (2,000 on the chain stage) |
-| `stage_thread.pt` | Parent of `chain.pt`: walk + carry + lift + thread | 7,497 |
-| `stage_lift.pt` | Parent of `stage_thread.pt`: walk + carry + lift | 5,498 |
-| `stage_carry.pt` | Parent of `stage_lift.pt`: walk + carry | 3,499 |
-| `generalist.pt` | Root of the chain: squat-capable walking with a commanded hand target; no basket | 2,000 |
-| `banks/standing_states.pt` (+ `.json`) | 5,000 harvested standing states used to initialize episodes | — |
-| `banks/squat_states.pt` (+ `.json`) | 5,000 harvested squatting states used to initialize the lift and thread stages | — |
-| `hero_video.mp4` | 60 s demo: full chain, threading close-up, robustness, failure case, ablation | — |
+| File | What it is | Cumulative PPO updates | Checkpoint index |
+|---|---|---:|---|
+| `chain.pt` | **The final policy** — the full task | 9,500 (2,000 on the chain stage) | `model_9495` |
+| `stage_thread.pt` | Parent of `chain.pt`: walk + carry + lift + thread | 7,500 | `model_7496` |
+| `stage_lift.pt` | Parent of `stage_thread.pt`: walk + carry + lift | 5,500 | `model_5497` |
+| `stage_carry.pt` | Parent of `stage_lift.pt`: walk + carry | 3,500 | `model_3498` |
+| `generalist.pt` | Root of the chain: squat-capable walking with a commanded hand target; no basket | 2,000 | `model_1999` |
+| `banks/standing_states.pt` (+ `.json`) | 5,000 harvested standing states used to initialize episodes | — | — |
+| `banks/squat_states.pt` (+ `.json`) | 5,000 harvested squatting states used to initialize the lift and thread stages | — | — |
+| `hero_video.mp4` | 60 s demo: full chain, threading close-up, robustness, failure case, ablation | — | — |
+
+Checkpoint indices are rsl_rl iteration indices, which undercount cumulative
+updates by one per resume; the update column is the number of PPO updates. The
+staged pipeline additionally used a separate 1,500-update reach policy plus
+state-bank harvesting to produce the banks above.
 
 Each checkpoint is an rsl_rl `OnPolicyRunner` save (actor, critic, optimizer
 state). The banks are required for evaluating or fine-tuning any stage other
@@ -47,20 +52,40 @@ from bank states.
 
 ## Results (`chain.pt` with the repository's commander)
 
-Full task: **98.4 ± 0.5 %** success over 500 episodes under each of 3
-evaluation seeds. Zero falls, zero baskets knocked away, no drops at the
-nominal configuration.
+All numbers use this one checkpoint (training seed 42), three evaluation
+seeds, 500 episodes 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).
+- 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 %).
+
+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** |
 |---|---|---|---|---|---|
 | Success | 98.7 % | 95.9 % | 98.9 % | 82.2 % | **98.4 %** |
 
-Robustness (one policy, no retraining): success is flat across handle openings
-of 15–35 cm (trained on 25 cm) and basket masses of 0.3–1.5 kg (trained on
-0.4–1.0 kg). Basket-pose observation noise is the limiting input: above 97 %
-up to 5 cm of position noise, 23.5 % at 10 cm (time-outs, not falls). On a
-spawn distribution the state machine was never tuned on (basket 1–3 m away,
-±90°, 15 s episodes) the chain succeeds in 98.6 % of 500 episodes.
+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:
+94.6 %, at 35 cm; trained on 25 cm) and was flat
+across basket masses of 0.3–1.5 kg (trained on 0.4–1.0 kg). Among the
+variables tested, basket-pose noise had the largest effect. The noise is
+bounded uniform per Cartesian coordinate with the stated half-width (the policy
+and the state machine share the observation model and bounds but draw
+independent samples): above 97 % up to a 5 cm half-width, 23.5 % at 10 cm
+(time-outs, not falls; sweep numbers use the reached-carry metric). On a spawn
+distribution the state machine was never tuned on (basket 1–3 m away, ±90°,
+one evaluation seed, 15 s episodes) the chain reaches 98.2 % strict success
+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