Upload with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -1.10 +/- 1.81
+      value: 16.30 +/- 10.73
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 50000, "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": 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 sha256:65d45c315285555a34617dc1ea6a549cdb5a5a30a3ece8ce75278a9b0619e113
-size 38983
+oid sha256:5725a06b9c88152627a40f0b3f39d58be08232dd62cd342489209f3428772860
+size 7251

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -1.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-09T06:43:09.908956"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-09T09:27:50.549979"}