Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 1.40 +/- 3.10
+      value: 14.40 +/- 14.62
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 1000, "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:a01e101a9c6db15a110ea600ae2ec09395fa32f54bec0d904e4f4cb7fb5b1624
+oid sha256:866a059cd1e6790c2213ff841e630ab31f8507ac3e1311c1542fec48973542c5
 size 39403

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 1.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-04T19:32:54.611285"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 14.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-04T19:38:04.076067"}