Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 13.50 +/- 11.47
+      value: 46.10 +/- 25.56
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 30000, "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:a0d54ec83339565efca9bdc5681cebeb3e1af070472bef95026917add1837af7
+oid sha256:b75c205a8269d87fc8e41cb610ad1e38c8345092ea1a94e1af3a778cab64a9f4
 size 38983

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 13.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-16T13:23:46.440286"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 46.1, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-16T16:41:34.921181"}