Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -5.00 +/- 0.00
+      value: 14.40 +/- 12.98
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 256, "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}
+{"h_size": 64, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0003, "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:de0af1788066ebf799b88ea0c99c13de9f1e56df650f638270be37b3175f909b
-size 541255
+oid sha256:2fffd996c0286ad380970c3bf58e14818c1ba0a5a1cb3f9cf91a3cfc18609b10
+size 39239

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -5.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-02T09:02:12.836636"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 14.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-04T11:23:32.489904"}