Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 34.10 +/- 31.17
+      value: -5.00 +/- 0.00
       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": 60000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.99, "lr": 0.0002, "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 sha256:8eca9e739535515f9b9068479640f26f8a310e48b1595f1c3516006d57d9c01d
-size 22023
+oid sha256:617bc6b69948beb35592b1a36a3ab7637d24b6fe48fae48d21b02c95031fe476
+size 141063

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 34.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-20T08:29:35.998693"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -5.0, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-20T16:34:36.389257"}