Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 8.10 +/- 14.17
+      value: 36.30 +/- 26.71
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 5000, "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": 15000, "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:e6edffe6565553401dc166f8d2579042948ed9981476f81f37668d18afa6455b
-size 39239
+oid sha256:fb29eb05b41aeba178fa2489e23439417c5402f0daf86c5d2c043e4f4b788b95
+size 39175

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 8.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-15T16:39:07.405037"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 36.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-16T08:05:01.581736"}