Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -2.60 +/- 0.49
+      value: 39.50 +/- 37.28
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 5, "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": 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:dad4bc1430e3fa992875581d4e78caac507657afe1137da5f93775b6289446ae
+oid sha256:f364f6c83240fbb7d27a739a2c4374bc6d492d539a6417c47c76b9d1eb113b0a
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.6, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-05T09:31:50.186777"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 39.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-05T11:14:54.977828"}