Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 18.60 +/- 20.80
+      value: 54.10 +/- 55.94
       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": 5e-05, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 128, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.98, "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 sha256:43098829c38b7c88fbc08b913b64c37b24fa6e336833ef2f317642f9f959c762
-size 541255
+oid sha256:b47559bc2f596965d6648dbcfc738c3b37c38e72ce1fa50109641f1da687c636
+size 140871

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 18.6, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-24T16:05:43.960416"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 54.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-29T13:34:41.299418"}