Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 29.10 +/- 28.09
+      value: 19.00 +/- 13.38
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"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}
+{"h_size": 16, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 1000, "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 sha256:6dbab9c1dcc17ce474e4afff9a7ff5964fe7cece6704a31b28f526a6f7ecc3e9
-size 12871
+oid sha256:5a7f74bcef0311fabf5af8c70fa4a4409eae1d908a0bb6e09662862e83d3fc59
+size 5831

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 29.096, "n_evaluation_episodes": 5000, "eval_datetime": "2023-04-15T22:53:09.697465"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 19.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-21T00:34:16.468986"}