Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 45.70 +/- 42.90
+      value: 20.00 +/- 14.85
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 30000, "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": 25000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 5e-05, "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:dcd9c3ec60f2077702aaac6851d987f456605ebe045260237ddba4cd181de29b
+oid sha256:8ab3f3a01ae86f93ed4db2f7e9e0adb79cd321c2cff7bea2121503790bacf74e
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 45.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-22T20:00:21.789750"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 20.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-03T09:40:41.008202"}