Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 23.50 +/- 14.22
+      value: 33.50 +/- 36.34
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 20000, "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": 128, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 5e-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 sha256:3619d0e8bd08eb24de22f9cd597628f78ccbdf0ee17c351d1ec4cddac33fa514
-size 38983
+oid sha256:4f4e7756554632cec20ed38ce93a6165993dde6bc93e8004ef26bf6a63a4a1f0
+size 140871

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 23.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-05T19:28:36.848000"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 33.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-06T03:09:44.547784"}