Upload final trained model

README.md

@@ -32,7 +32,7 @@ model-index:
             value: TBD
 pipeline_tag: reinforcement-learning
 metadata:
-  utc_timestamp: 2025-12-11T22:08:55.460407
+  utc_timestamp: 2025-12-11T23:10:57.765783
   env_name: UTDGEnv-v0
   model_file: model_policy.zip
   total_timesteps: 0
@@ -130,15 +130,16 @@ metadata:
         "curriculum": {
           "enabled": true,
           "initial_max_steps": 1200,
-          "step_increase": 200,
+          "step_increase": 50,
           "reward_thresholds": [
+            -50.0,
+            -25.0,
             0.0,
-            5.0,
-            10.0,
-            30.0,
-            50.0
+            25.0,
+            50.0,
+            100.0
           ],
-          "window_size": 30,
+          "window_size": 20,
           "max_steps_cap": 10000
         }
       },
@@ -398,4 +399,4 @@ If you use this model in your research, please cite:
 
 ---
 
-*Generated on 2025-12-11T22:08:55.460407 UTC*
+*Generated on 2025-12-11T23:10:57.765783 UTC*

models/model_policy.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70e2be5f66381833152bec1b137ca30bd1f8e3184e14bdf9b8cded2916d7f2e8
-size 649184
+oid sha256:b28493858a33cef4a49d271646dbaa7c87498d1cac0e97d4c5274be6bb2e9b63
+size 649395