Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 22.65 +/- 18.35
+      value: 15.00 +/- 10.70
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 5000, "n_evaluation_episodes": 20, "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": 500, "n_evaluation_episodes": 5, "max_t": 100000, "gamma": 0.999, "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:a68d1e6c9d6c9ed7e0fa8cb17a6651b2812fcaccefa6ad62268883f8895af049
+oid sha256:728290ce936985b77b2df09071859fb12243d692a655cc7155cae82eaa1bda9d
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 22.65, "n_evaluation_episodes": 20, "eval_datetime": "2023-03-07T16:57:43.564218"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 15.0, "n_evaluation_episodes": 5, "eval_datetime": "2023-03-07T17:45:40.580051"}