Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 16.20 +/- 13.31
+      value: 15.80 +/- 15.37
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "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": 30000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.999, "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:e2df8fd76b41ee01873d67924761f8b85a86aefa35d59034e6f362cec9f86b3d
+oid sha256:7959fc5a27077d8e8286817bbe4d5cac8b6ac8e3fc68f0d44390af51c84a462b
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-20T08:42:57.197113"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 15.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-21T11:22:14.923236"}