Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -0.70 +/- 2.79
+      value: 53.60 +/- 43.74
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 100, "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": 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:a8db2abbf79c53021900a0dbf439f50703c28eb0ede3a7d2f0cd5699df5c1c4b
+oid sha256:18b836d9ec6f43421276b3ed79e22b517dcf7a4646ef2125e2d6281864b24d0d
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -0.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-09T09:40:53.270163"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 53.6, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-09T12:27:37.903659"}