Increase training steps

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: -5.00 +/- 0.00
+      value: 103.20 +/- 106.61
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 100, "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": 200000, "n_evaluation_episodes": 10, "max_t": 200000, "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 sha256:309ddb102abcbebf244d81e20df2ac8489871a35619c6d2eaa372b638e4339fc
+oid sha256:85b13a03da61257c658c4dcbf0ade6fbdf029d1f3ba6bc4b74d91cb0e1409c51
 size 39924

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": -5.0, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-17T15:09:26.242088"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 103.2, "n_evaluation_episodes": 10, "eval_datetime": "2024-03-18T17:54:23.089518"}