publish backroll: perpetual, Mjlab-GotATalent-MicroDuck

README.md

@@ -29,7 +29,7 @@ The observation normalizer is baked into `policy.onnx`; feed raw observations.
 - **repo**: `https://github.com/bxshi/microduck-challenges.git`
 - **branch**: `HEAD`
 - **commit**: `a15317f40`
-- **checkpoint**: `1250`
+- **checkpoint**: `1750`
 - **seed**: `1`
 - **base**: `mjlab-microduck 0.1.0 @ 8d0dbc94c`
 - **started**: `2026-10-22T07:55:17Z`

checkpoint.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb0060e518c33ec04f866091b6417dada21b2a0af26ac3217a00d45974e5abf
+oid sha256:4c4aa15f54c2cd8019c6f1fade3412041189c3d7c134485cf8d179079e2393eb
 size 4849589

manifest.json

@@ -55,8 +55,8 @@
     "base": "mjlab-microduck 0.1.0 @ 8d0dbc94c",
     "started": "2026-10-22T07:55:17Z",
     "task_id": "Mjlab-GotATalent-MicroDuck",
-    "checkpoint": 1250,
-    "source_file": "model_1250.pt"
+    "checkpoint": 1750,
+    "source_file": "model_1750.pt"
   },
   "arena": {
     "event": "got-a-talent"

policy.onnx

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d9ee9b7c47dc9407a3a4862b9904d14742a59fc47be27d783f661c32a6d50
+oid sha256:4da30d56c382f5b7de0dbe345e6d7d3340f967112682e57a01d5d4a87fda72f6
 size 793757