Upload final trained model

README.md

@@ -32,7 +32,7 @@ model-index:
             value: TBD
 pipeline_tag: reinforcement-learning
 metadata:
-  utc_timestamp: 2025-12-13T00:09:03.011949
+  utc_timestamp: 2025-12-15T00:05:15.498819
   env_name: UTDGEnv-v0
   model_file: model_policy.zip
   total_timesteps: 0
@@ -122,23 +122,22 @@ metadata:
         "max_grad_norm": 1.0
       },
       "training": {
-        "total_timesteps": 800000,
+        "total_timesteps": 200000,
         "device": "auto",
         "log_interval": 2048,
         "progress_bar": true,
         "verbose": 1,
         "curriculum": {
-          "enabled": true,
-          "initial_max_steps": 1200,
-          "step_increase": 50,
+          "enabled": false,
+          "initial_max_steps": 500,
+          "step_increase": 1000,
           "reward_thresholds": [
-            5,
-            10,
-            15,
-            20,
+            -50,
+            -25,
+            0,
             25,
-            40,
-            60
+            50,
+            100
           ],
           "window_size": 20,
           "max_steps_cap": 10000
@@ -400,4 +399,4 @@ If you use this model in your research, please cite:
 
 ---
 
-*Generated on 2025-12-13T00:09:03.011949 UTC*
+*Generated on 2025-12-15T00:05:15.498819 UTC*

models/model_policy.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba0c4eeb9a7d93a5a678d7882ae381c3fea0b1153e681a14061ffaabc7136e1b
-size 650362
+oid sha256:9ff9b54f638a6b1b3731ab9241d9c4a36541b729a4e6600560ad0125cbbe7469
+size 647003