Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 22.40 +/- 26.62
+      value: 36.70 +/- 34.71
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "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}
+{"h_size": 64, "n_training_episodes": 60000, "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 sha256:0c38dd53e290cd58a2c03e2c95ca578aa3506506e8cb415ef3a7909d9ed7eca7
-size 140871
+oid sha256:b15af96d047f30fdd6db1bd178c1c1810b8ea5f25c92c56af249a92a50acb257
+size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 22.4, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-07T16:41:17.119872"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 36.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-10T12:55:37.410789"}