Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 16.50 +/- 19.04
+      value: 79.60 +/- 69.67
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 10000, "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": 100000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 5e-05, "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:a6bcc7154cdd12fc8d5cc1f73baf3848ffdcc53b667873afb440e8b531682a4f
-size 38999
+oid sha256:523923618a994da26465c556137d66c2b5091e91b58c705747d4ff07da82efcc
+size 140887

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 16.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-11T11:19:53.873005"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 79.6, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-11T16:28:16.407140"}