Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 13.90 +/- 17.83
+      value: 18.07 +/- 19.03
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "n_training_episodes": 10000, "n_evaluation_episodes": 30, "max_t": 5000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 128, "n_training_episodes": 20000, "n_evaluation_episodes": 30, "max_t": 5000, "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 sha256:1fed4d4043a4e53a23bb22b44bdbaa1b62d03182a31c363eee5415f6088659b8
-size 140871
+oid sha256:b42105cead5ee43cd999a0fbd2a6792d67e68606cda00303ebe7ca25f9d62570
+size 140807

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 13.9, "n_evaluation_episodes": 30, "eval_datetime": "2023-03-09T16:30:31.040992"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 18.066666666666666, "n_evaluation_episodes": 30, "eval_datetime": "2023-03-09T17:55:16.571464"}