Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -2.70 +/- 0.46
+      value: 7.70 +/- 10.00
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 32, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.95, "lr": 0.01, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 128, "n_training_episodes": 100000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 1e-05, "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 sha256:2dfd4ba0ab1d44fa1ba0d2a9e87c4b5dc1a2def9594ca3b20b21a15800c2ceaf
-size 12615
+oid sha256:88252bb430f863dfe6a808e103ff9f7d502bb12d11b090e9bc0b03439459e139
+size 140871

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-07T23:10:53.637773"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 7.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-10T20:05:46.092435"}