Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 13.00 +/- 12.37
+      value: 58.50 +/- 53.06
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "n_training_episodes": 25000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.98, "lr": 0.0001, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 68, "n_training_episodes": 50000, "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:c19ad413e91a3ed4c0405a420810d6b3e99677942d4cc86f9af5ae9233d42359
-size 140807
+oid sha256:52757c7ed7c66da0a5a74410e809a6e2b3f6d2c219a711c052e423df69bcbb7c
+size 43463

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 13.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-14T13:33:39.815547"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 58.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-14T20:00:04.281629"}