Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 47.20 +/- 44.25
+      value: 41.50 +/- 36.13
       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": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.999, "lr": 1e-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 sha256:849d9171216bd63f009ee74848217584b9af52e955a9d87e3c94bdc5e4dd17c8
+oid sha256:6c2b22df6bace4fde46d3cceb994bd856a02344f4327642c9bfc018b7f6c818e
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 47.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T06:48:56.181952"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 41.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-04T06:55:11.595820"}