Upload folder using huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 24.40 +/- 19.56
+      value: 39.90 +/- 29.33
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 50000, "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": 80000, "n_evaluation_episodes": 10, "max_t": 1000000, "gamma": 1.0, "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 sha256:456334ff0bbfc5c67c05e95633e137c0306f68c0b13fc77bb0762dfeca9ab1d0
-size 39668
+oid sha256:43e2b92cce3c818c95291f2d010d38a1c707efb0a5977927cca72b4631a51438
+size 39732

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 24.4, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-30T00:26:19.045975"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 39.9, "n_evaluation_episodes": 10, "eval_datetime": "2024-04-12T05:23:26.495972"}