Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 42.31 +/- 38.89
+      value: 29.10 +/- 28.09
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "n_training_episodes": 50000, "n_evaluation_episodes": 5000, "max_t": 5000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 32, "n_training_episodes": 30000, "n_evaluation_episodes": 5000, "max_t": 3000, "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 sha256:8cd9d06dd518181322f6450a788e80c2ffb1260d86b61789bf716cac59034e90
-size 141127
+oid sha256:6dbab9c1dcc17ce474e4afff9a7ff5964fe7cece6704a31b28f526a6f7ecc3e9
+size 12871

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 42.3072, "n_evaluation_episodes": 5000, "eval_datetime": "2023-04-13T20:47:05.606958"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 29.096, "n_evaluation_episodes": 5000, "eval_datetime": "2023-04-15T22:53:09.697465"}