Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 8.90 +/- 10.53
+      value: 28.80 +/- 24.24
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 500, "n_training_episodes": 50000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.999, "lr": 1e-05, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 500, "n_training_episodes": 15000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.999, "lr": 5e-05, "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 sha256:617b910d6e3b3e33479265df522831957700ac1b767d267148f4438731be6db5
+oid sha256:e5ced398f85d8a30d45e8b165a7a17f86bb4d6ea14d978c2fc38d257ae5971e6
 size 2031047

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 8.9, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-13T00:50:16.985399"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 28.8, "n_evaluation_episodes": 10, "eval_datetime": "2023-01-15T05:23:32.786872"}