Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 32.90 +/- 34.90
+      value: 45.10 +/- 32.53
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 32, "n_training_episodes": 25000, "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": 16, "n_training_episodes": 30000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.9, "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 sha256:00c744f789055e3b6304212fc8e88cf6c3d57cb54d71f352f5a50ce179cbbea7
-size 13511
+oid sha256:a342f4ad477cc30f5a5aefdd374c1324ac1b00a7f4f9217e0cbec6e66abc101c
+size 6087

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 32.9, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-19T10:24:55.123904"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 45.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-20T05:38:24.404885"}