Upload . with huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -2.70 +/- 0.46
+      value: 22.50 +/- 16.85
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "n_training_episodes": 500000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.975, "lr": 0.0005, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 128, "n_training_episodes": 500000, "n_evaluation_episodes": 10, "max_t": 10000, "gamma": 0.98, "lr": 0.0003, "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 sha256:324ca59b3b6b1c33abf7e1a04921f6a01d1aeeec2debb08b206df06721e7c5df
+oid sha256:0e7cb69fc3acd1843f6c933f4d7c1447919ed3261366738575abba8787e54cb0
 size 140887

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -2.7, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-15T15:31:33.654811"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 22.5, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-15T19:41:35.340527"}