Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 16.80 +/- 12.77
+      value: 65.80 +/- 49.73
       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": 64, "n_training_episodes": 100000, "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 sha256:8f22107dc4b062e90a425d25bb707ae1c4bd64d0119f9caf72a4b48a6aec134f
+oid sha256:b9f0a76fd03d6c338142193bd9e52bffb47a2cb9e320e19f0bbc577220525218
 size 39175

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-26T18:24:54.742859"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 65.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T01:50:00.139742"}