Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 41.10 +/- 39.45
+      value: 7.50 +/- 8.57
       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": 128, "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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:643752cf521abef5ef852bb7b8e325645a98183f82f931bacda016f00db5d0f0
-size 39239
+oid sha256:503fe9cb47aa2a99d5ffea5eb62233b14242a80bec38873c07f94d6a31df70df
+size 141127

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 41.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-10T09:36:34.776711"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 7.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-18T10:07:02.215376"}