Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 64.00 +/- 60.08
+      value: 23.70 +/- 17.14
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 128, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.999, "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 sha256:2191770b78e60c4e3595b17ad64661b8692fe99c78cec04b58868eac34d7c751
-size 38919
+oid sha256:d0a951af5681858463c6ac8e14e9df38030cfb6230321458a38d97fb0e9c6d20
+size 140807

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 64.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T16:31:50.096221"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 23.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-29T15:08:06.694751"}