Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 0.00 +/- 0.00
+      value: 72.90 +/- 30.43
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 1, "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": 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.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42fc3641d6e247ab4cd9fb94247634b279bf383c6bbda66641204b8a16f6d2b6
+oid sha256:d73bd6db62ed3d51bd672873426242bbda2ebaaf21e226edd63f2e6ec1c38ef9
 size 142180

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 0.0, "n_evaluation_episodes": 1, "eval_datetime": "2023-03-07T22:06:30.274541"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 72.9, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-07T22:07:08.350817"}