Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 9.40 +/- 15.38
+      value: 33.10 +/- 28.05
       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": 30000, "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:eb694fbb8bfeef16189b7ce25eb465f8d380f24a6fe6444f753bb0316b94b882
+oid sha256:b1add1506716268e1e5f9bdf0a8f0a1bf1dc7328bf00429603e9712613eb1e33
 size 21831

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 9.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-30T20:19:51.086101"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 33.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-30T21:36:57.228468"}