Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -2.70 +/- 0.46
+      value: 21.20 +/- 13.90
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.98, "lr": 0.0005, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 100000, "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 sha256:11cb46ee4f350c54391d3c449c67d39818bf9af469e09463904fa2bd679b387b
-size 39239
+oid sha256:997d20223b1cff84d8294f32022e9b314d0fdb2f9f74e870d362e3d8c651dbee
+size 38935

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-07T18:20:01.775643"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 21.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-22T21:24:04.425619"}