Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 22.00 +/- 21.02
+      value: 47.00 +/- 37.05
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.95, "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": 0.99, "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:c008102ecbc3dde99a8368ccd8276b76476c015167176b8ada2c416dd69b4bdb
-size 21831
+oid sha256:b5f2b6c158cfbe4cccc8d57bf20c4dc1bc4167f8c96f48b0df4e85bdd2dd4df4
+size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 22.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-06T15:56:29.514352"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 47.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-11T11:31:27.020482"}