Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 20.10 +/- 17.69
+      value: 11.80 +/- 9.25
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 15000, "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": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.7, "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:ddb1873c2ba3b9e35f33630012b5b2aa49ae644ec7fbbdc6367777747b92ba56
-size 38919
+oid sha256:5727b6892c3dfd25616c897bb9e9f4b1a04302abdc1a321b1d0d20707253edb5
+size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 20.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-07T21:27:19.187044"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 11.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-07T22:43:03.897621"}