Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 34.40 +/- 27.53
+      value: 16.20 +/- 19.31
       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, "weight_decay": 1e-06, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "weight_decay": 1e-08, "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:e53eaa7cc93ec22d1d9e6be664331b03de3843455965a804dd4127e445d282f5
-size 136897
+oid sha256:e70f7d6806881cae70fb6b34432127b63aa290e1bfce50a9cd8a8b121a2384ad
+size 136455

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 34.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-06T13:56:39.055384"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-06T22:36:41.885769"}