Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 11.60 +/- 12.62
+      value: 16.10 +/- 9.95
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 5000, "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": 10000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0005, "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:bb71cbdf3c16fa36a0e0eb54e8b4f8e515f204e253c7ef731ef2b85cce15ba8a
+oid sha256:be2924335c4a4a75c537a9030565466fc8b6c62ec0ecd63908078dcb34022ad1
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 11.6, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-06T05:25:17.732215"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-06T15:59:38.068806"}