Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 19.10 +/- 21.03
+      value: 17.20 +/- 10.39
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "n_training_episodes": 20000, "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": 256, "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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf03a9f8763b489016aaacf60922d12df1d7ff2076edebdde401275552b5c3c9
-size 140807
+oid sha256:02f76cddc484f22b37c77c8985b5155f4a296fc6201b74b055467a82c818e981
+size 541255

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 19.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-13T06:47:57.882219"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 17.2, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-13T09:14:40.073071"}