Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 8.20 +/- 10.40
+      value: 18.90 +/- 18.51
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 8, "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": 8, "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 sha256:56272c3abad49e4d05a96c47a5d94e9d3b64a90d2121ecf562ab5a1f96862f39
-size 3143
+oid sha256:65c19cd3a490234200da937a1bf2fffcad5cfb3a043684ce273ff5b7da0490b4
+size 3771

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 8.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-09T22:26:23.906131"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 18.9, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-10T00:06:33.335699"}