Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 8.50 +/- 12.32
+      value: 29.30 +/- 18.72
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 5000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.999, "lr": 8e-05, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1579d85f9ab78b8016d4fbb1acc424cc79c6d351f81e4ebdee77ebdf1254e3ef
+oid sha256:04fe67eca34831320dc9c39cb9cf67ccbd6df8f1890cf716970d1a8f5f0ff641
 size 22215

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 8.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-07T06:44:17.882740"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 29.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-07T06:57:17.399604"}