Upload folder using huggingface_hub

README.md

@@ -16,9 +16,33 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 8.50 +/- 10.00
+      value: 27.50 +/- 21.88
       name: mean_reward
       verified: false
 ---
-# Reinforce Agent playing Pixelcopter-PLE-v0
-Unit 4 Deep RL Course.
+
+# REINFORCE Agent - PixelCopter-PLE-v0
+
+Trained with the REINFORCE algorithm.
+
+## Results
+
+| Mean reward | Std reward |
+|-------------|------------|
+| 27.50       | 21.88      |
+
+## Hyperparameters
+
+```json
+{
+  "h_size": 64,
+  "n_training_episodes": 20000,
+  "n_evaluation_episodes": 10,
+  "max_t": 10000,
+  "gamma": 0.99,
+  "lr": 0.0001,
+  "env_id": "Pixelcopter-PLE-v0",
+  "state_space": 7,
+  "action_space": 2
+}
+```

hyperparameters.json

@@ -1 +1,11 @@
-{"h_size": 64, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{
+  "h_size": 64,
+  "n_training_episodes": 20000,
+  "n_evaluation_episodes": 10,
+  "max_t": 10000,
+  "gamma": 0.99,
+  "lr": 0.0001,
+  "env_id": "Pixelcopter-PLE-v0",
+  "state_space": 7,
+  "action_space": 2
+}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ee1b7ef565bb6b4aee611a5581b7db96a6486ba13ad522ee68ae7aed23a88e6
-size 40125
+oid sha256:b868f80f3eb62650786bac19b5fc26ca7e6efc8cdc414b17edb603f4e699ef86
+size 40189

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 8.5, "n_evaluation_episodes": 10, "eval_datetime": "2026-03-18T22:14:44.443965"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 27.5, "std_reward": 21.88}