Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 16.90 +/- 14.94
+      value: -2.70 +/- 0.46
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "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": 256, "n_training_episodes": 50000, "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:a0e585f6b0ca710f0a01c92ff8762a47015789fb1237a4eab1029eee16588f79
-size 22279
+oid sha256:827b58303545d04137064cd04fb42146468522d958e4c5c465d476e0f006c609
+size 540283

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.9, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-08T10:13:22.817350"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-08T10:33:50.637180"}