Upload policy weights, train config and readme

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5466d09e5876809a52ce8d9790dd5ccbc3da031f142af7a83a1edaa4a489800b
+oid sha256:fdd54ddcf8c6074a24cf4393d1d1748bdcbb3da78338821a33196895b4ccb7a0
 size 7473096344

train_config.json

@@ -155,7 +155,7 @@
     "seed": 1000,
     "num_workers": 4,
     "batch_size": 32,
-    "steps": 12000,
+    "steps": 13000,
     "eval_freq": 20000,
     "log_freq": 200,
     "save_checkpoint": true,