Upload . with huggingface_hub

README.md

@@ -8,17 +8,16 @@ tags:
 model-index:
 - name: Reinforce-pixelcopter
   results:
-  - task:
+  - metrics:
+    - type: mean_reward
+      value: 5.80 +/- 4.31
+      name: mean_reward
+    task:
       type: reinforcement-learning
       name: reinforcement-learning
     dataset:
       name: Pixelcopter-PLE-v0
       type: Pixelcopter-PLE-v0
-    metrics:
-    - type: mean_reward
-      value: 12.30 +/- 12.51
-      name: mean_reward
-      verified: false
 ---
 
   # **Reinforce** Agent playing **Pixelcopter-PLE-v0**

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 5000, "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": 1000, "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:fa8c8491f4584c81373272824bdfbd9c9a073e4e0e8aab8c79530f3303b5c689
+oid sha256:46454ffc528cfb8a89a29d7a7c7682e2c15489266f5f6ed8864c0ff0a1764889
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 12.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-06T09:15:26.812060"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 5.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-06T19:34:59.610045"}