Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 9.20 +/- 6.85
+      value: 41.70 +/- 38.90
       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": 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 sha256:999d6e6ab892e7ad966bcb84329d63336d6454296dd73481a2bdee01b59a34c2
+oid sha256:14a33f835a5af9d9ea8ceecc33dc5e245bd24650c31e13d800ae9678b1abda43
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 9.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-06T10:53:45.979209"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 41.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-06T14:37:58.613007"}