Upload folder using huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 45.50 +/- 46.61
+      value: 29.80 +/- 22.68
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 16, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 2000, "gamma": 0.95, "lr": 0.0002, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 20000, "n_evaluation_episodes": 10, "max_t": 5000, "gamma": 0.98, "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 sha256:1a2bb08e03d8fd81020ddb95512a856894b0b35de692928b477d7578d7dd5257
-size 6324
+oid sha256:a98ae7b09bc34adb0c738346d904afdb465cd38a4528ca95f96211280fea1643
+size 39732

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 45.5, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-17T20:37:58.994363"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 29.8, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-17T22:05:11.393708"}