Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 8.50 +/- 18.15
+      value: 11.50 +/- 13.25
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 16, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 1000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 32, "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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0dcc036af81b828e4f6f6430a5192c373a101f20ee952a8dd9ffdd54c838a25
-size 5575
+oid sha256:fd9979ead2363765cbf80f9e22989a8269b6ef523c36c5880d14f8ca19bf3613
+size 12615

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 8.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-29T22:19:12.584684"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 11.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-29T22:36:39.396956"}