Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 16.80 +/- 13.44
+      value: 11.30 +/- 11.49
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 200, "n_training_episodes": 20000, "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": 212, "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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efe26767736fbe1fb3d92c58948c9b45b51fcf5f37384a43f72464109d2e0b98
-size 334151
+oid sha256:dba2d6800ab8663f1f4ecb4ece245625631f95f97d8470aaad9cd6a2ae4225b5
+size 374407

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-07T17:41:06.895353"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 11.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-07T19:30:57.434433"}