Upload policy weights, train config and readme

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546c534d7dd63e3f0f381b61719a1aa7a27700bc9c9e4f8c0659ef57f873a7d0
+oid sha256:9e71da8750f56e836fcb6fa95086255173adbc540370baabf82a7d4acbe43759
 size 33810140

train_config.json

@@ -141,7 +141,7 @@
             "VISUAL": "MEAN_STD"
         }
     },
-    "output_dir": "outputs/train/2025-10-23/13-56-12_hil-serl2-reward-classifier",
+    "output_dir": "outputs/train/2025-10-23/14-40-04_hil-serl2-reward-classifier",
     "job_name": "hil-serl2-reward-classifier",
     "resume": false,
     "seed": 2,
@@ -171,13 +171,13 @@
         "use_async_envs": false
     },
     "wandb": {
-        "enable": false,
+        "enable": true,
         "disable_artifact": false,
         "project": "hil-serl2-reward-classifier",
         "entity": null,
-        "notes": null,
-        "run_id": null,
-        "mode": null
+        "notes": "Reward classifier training (hil-serl2)",
+        "run_id": "ounj4wu6",
+        "mode": "online"
     },
     "checkpoint_path": null
 }