Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 22.20 +/- 26.71
+      value: -2.50 +/- 0.50
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.9, "lr": 0.0005, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 128, "n_training_episodes": 20000, "n_evaluation_episodes": 20, "max_t": 10000, "gamma": 0.99, "lr": 0.0005, "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 sha256:987001030fba2be3c7ee9a12e9d23585ce554b1189160e505a1365a856ecd858
-size 22151
+oid sha256:de0c7be505c00c59c72a4e533334e7e3bc11a4eab0d61468a6690282c4df374a
+size 74119

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 22.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-10T15:42:19.037772"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.5, "n_evaluation_episodes": 20, "eval_datetime": "2023-01-10T15:50:53.890884"}