Upload folder using huggingface_hub

README.md

@@ -0,0 +1,78 @@
+---
+license: mit
+tags:
+  - robotics
+  - reinforcement-learning
+  - mimicgen
+  - visual-encoder
+---
+
+# IMPALA pixel encoder — MimicGen `threading_d0`
+
+The visual encoder from a DICE-RL pixel-Q critic that reaches **90% success** on MimicGen
+`threading_d0` (needle-through-tripod insertion), trained from 224x224 RGB with DrQ random-shift
+augmentation.
+
+## What this is
+
+Two IMPALA conv towers, one per camera, whose outputs are concatenated with 9 proprio dims:
+
+```
+images uint8 [B, 2, 224, 224, 3]  +  proprio [B, 9]
+        -> per-camera ImpalaTower (channels 16/32/32, residual blocks, 3x stride-2 pools)
+        -> 32 x 28 x 28 feature map, flattened -> Linear -> LayerNorm -> 128
+        -> concat([tower0, tower1, proprio]) = 265
+```
+
+6.6M parameters. Proprio is `eef_pos(3) + eef_quat(4) + gripper_qpos(2)`, StateScaler-scaled.
+
+## Loading
+
+```python
+import torch
+from online_rl_mimicgen.pixel import PixelEncoder      # PIXEL_IMG=224 must be set
+
+enc = PixelEncoder(out_dim=128)
+enc.load_state_dict(torch.load("impala_encoder.pt", map_location="cpu"))
+enc.eval()
+
+feats = enc(images_uint8, proprio_scaled)              # -> [B, 265]
+visual_only = feats[:, :256]                           # drop the proprio block
+```
+
+`PIXEL_IMG` is read from the environment at import time and fixes the head's input width, so it
+must be `224` before `online_rl_mimicgen.pixel` is imported. At the library default of 84 the
+`Linear` shapes will not match these weights.
+
+## What it encodes — measured, in millimetres
+
+Held-out state read-off (200 episodes, 20% held out **by episode**, 2-layer MLP head), against the
+same protocol applied to frozen mean-pooled DINOv2 features:
+
+| target | this encoder | frozen DINOv2 (768) |
+|---|---|---|
+| `eef_pos` | 33.3 mm | **15.8 mm** |
+| `obj_pos` (needle) | 30.2 mm | **17.3 mm** |
+| `goal_pos` (tripod) | **46.4 mm** | 73.7 mm |
+| offset (needle − tripod) | **47.9 mm** | 97.1 mm |
+| ‖offset‖ (scalar distance) | **31.7 mm** | 79.8 mm |
+
+The pattern is the useful part: this encoder is **worse at absolute positions and better at every
+relative quantity**. Task training reallocates precision toward the needle-hole relationship that
+TD learning needs, at the cost of world-coordinate localisation it does not — with a third of the
+feature dimensions.
+
+Note it resolves the offset to ~48 mm while solving a task whose tolerance is far tighter, so
+millimetre-accurate geometry is evidently not required for 90% success.
+
+## Provenance and caveats
+
+- Run `thrpix2_q_s42`, 300k env steps, DICE-RL model-free pixel Q (`--pixel-obs`, no world model).
+- Trajectory: 57% at 0k (BC prior) → 86% at 50k → 89% at 100k → **90% at 300k**.
+- **Trained WITH DrQ augmentation** (`random_shift`, pad=4 → ±1.79% of a 224 frame). This matters:
+  otherwise-identical runs **without** augmentation reach only **63.4%** (n=5) — augmentation is
+  worth ~+28 points here, so these weights should not be read as "what an IMPALA encoder learns"
+  independent of that regulariser.
+- A sibling seed reached 96%, but its checkpoint predates encoder saving and is unrecoverable;
+  this is the best encoder that actually exists on disk.
+- Single task, single simulator, two fixed camera poses. No claim of transfer.

config.json

@@ -0,0 +1,31 @@
+{
+  "architecture": "ImpalaTower x2 (one per camera) + concatenated proprio",
+  "task": "mimicgen threading_d0",
+  "image_size": 224,
+  "cameras": [
+    "agentview",
+    "eye_in_hand"
+  ],
+  "out_dim_per_tower": 128,
+  "output_width": 265,
+  "proprio_dim": 9,
+  "proprio_note": "eef_pos(3) + eef_quat(4) + gripper_qpos(2), StateScaler-scaled",
+  "params": 6618496,
+  "env_steps": 300007,
+  "trained_with": "DICE-RL pixel Q critic (model-free), DrQ random shift pad=4",
+  "pixel_augment": true,
+  "drq_shift_pad": 4,
+  "success_rate": {
+    "0k": 57,
+    "50k": 86,
+    "100k": 89,
+    "300k": 90
+  },
+  "state_readoff_rms_mm": {
+    "eef_pos": 33.3,
+    "obj_pos_needle": 30.2,
+    "goal_pos_tripod": 46.4,
+    "offset_vector": 47.9,
+    "offset_scalar": 31.7
+  }
+}

impala_encoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:405a7daaf09d64484bed5c3b641288cb69c3d8a17c62bd3f5dfdad72aa166cef
+size 26498013