Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 16.00 +/- 12.43
+      value: 20.30 +/- 13.77
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfcaed3323e53062a6e5ad4ec125bef9bf2153a9b24bce4cc29c8fcb298f136a
-size 38983
+oid sha256:d35f8be2917848a95b12c41882ce8c902bf6eb20732a7d970db11f881f63bc1e
+size 38919

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-08T01:41:00.839196"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 20.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-08T03:34:47.668501"}