Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 9.80 +/- 9.45
+      value: 21.80 +/- 16.40
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "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": 0.0001, "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:fbc7d5989e8d024905047ba37ad950eaaa93222f5abca82a16db6254c51d587b
+oid sha256:7099c687d10bff7c8e5c311af6b1debc06f884cfa0d5ac7a393dadc9f33c8b6f
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 9.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-06T14:11:19.080160"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 21.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-08T12:15:14.893463"}