Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 18.20 +/- 19.11
+      value: 2.20 +/- 3.97
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "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}
+{"h_size": 128, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 1, "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 sha256:606dc7d0b426a63fa5337657444b1fd0718d2e8a0d38667b5793805a0973fab3
-size 38983
+oid sha256:b534e672dace504599f73ef616de7eea6f8b7d996d9174b36cb48e8eb4e7321a
+size 798843

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 18.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-22T05:09:22.082727"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 2.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-23T23:02:01.880306"}