Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 43.00 +/- 38.63
+      value: 14.30 +/- 18.76
       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": 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}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:786a48578b81ec6d459cf3ea1603a77bd9b204ada4c35cbef6aab4f11bcac993
-size 38983
+oid sha256:0c38dd53e290cd58a2c03e2c95ca578aa3506506e8cb415ef3a7909d9ed7eca7
+size 140871

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 43.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-07T15:15:10.332721"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 14.3, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-07T16:38:47.278318"}