Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -5.00 +/- 0.00
+      value: 25.50 +/- 21.62
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 256, "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": 64, "n_training_episodes": 40000, "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 sha256:8dddf85d6393ca255e889985e835f44a6f15cbbdef4c2edad5f09388b6de9852
-size 541255
+oid sha256:159e2c5098a4a1b80a925d168b5cabf6e40eb0f636daa02ff0c2010c4c26302e
+size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -5.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-18T00:39:43.283639"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 25.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-18T20:12:28.418796"}