Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 22.00 +/- 41.92
+      value: 53.00 +/- 42.68
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 200, "n_training_episodes": 60000, "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": 100000, "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:a6dddc625508982c930e065cb0ec2cb7862caba995f010a790b67c9995cbbc8d
-size 333831
+oid sha256:d9d7ebc6345f0537966876e0baca9f99abe942f2a1a04aa1acaec56b45760e9e
+size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 22.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-30T13:50:53.989412"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 53.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-15T23:57:57.006832"}