Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 22.20 +/- 19.99
+      value: 55.90 +/- 40.18
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 2000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.7, "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": 0.99, "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 sha256:593891b97383dd5333477565e9774e74df39b377eab9e66abd1d6299f78fbe36
+oid sha256:ebb34436b606a45ed9975faf14701031a7901df10a84beb4ac35bc8c46a6973d
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 22.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-09T06:14:50.051661"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 55.9, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-10T05:52:47.663085"}