Upload folder using huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: Pixelcopter-PLE-v0
     metrics:
     - type: mean_reward
-      value: 7.60 +/- 12.51
+      value: 23.00 +/- 0.00
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 128, "n_training_episodes": 10000, "n_evaluation_episodes": 50, "max_t": 2000, "gamma": 0.98, "lr": 1e-05, "epsilon_start": 1.0, "epsilon_decay": 0.99, "epsilon_min": 0.01, "batch_size": 128, "buffer_size": 100000, "prioritized_replay": true, "env_id": "Pixelcopter-PLE-v0", "state_space": 7, "action_space": 2}
+{"h_size": 64, "n_training_episodes": 20000, "n_evaluation_episodes": 1, "max_t": 10000, "gamma": 0.99, "lr": 0.00015, "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:e09a5e271f6dfa6adb255c017bed077e48f406d11589a1eab4f9f85e2b6e4d98
-size 141556
+oid sha256:9d838ad071a95b0ba187f6cb613a27e1ec826d37090de6e83c78d007628ebdde
+size 39668

results.json

@@ -1 +1 @@
-{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 7.6, "n_evaluation_episodes": 50, "eval_datetime": "2024-09-25T18:14:03.364634"}
+{"env_id": "Pixelcopter-PLE-v0", "mean_reward": 23.0, "n_evaluation_episodes": 1, "eval_datetime": "2024-09-25T19:26:03.939340"}