Upload folder using huggingface_hub

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 102.45 +/- 49.34
+      value: 152.71 +/- 63.40
       name: mean_reward
       verified: false
 ---

hyperparameters.json

@@ -1 +1 @@
-{"h_size": 64, "n_training_episodes": 2000, "n_evaluation_episodes": 10, "max_t": 500, "gamma": 1, "lr": 0.001, "env_id": "LunarLander-v2", "state_space": 8, "action_space": 4}
+{"h_size": 64, "n_training_episodes": 10000, "n_evaluation_episodes": 10, "max_t": 400, "gamma": 0.995, "lr": 0.001, "env_id": "LunarLander-v2", "state_space": 8, "action_space": 4}

model.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4a118d384b71f44e0e3a65b5bb3eb7a70619dd13ef8d269cabddf3387f54fce
+oid sha256:6555fa750601cee2aa77404a0d47204477ddd32c84c3a0af5d077a76f7374941
 size 41012

results.json

@@ -1 +1 @@
-{"env_id": "LunarLander-v2", "mean_reward": 102.4472013654035, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-11T13:48:39.085047"}
+{"env_id": "LunarLander-v2", "mean_reward": 152.70516317050948, "n_evaluation_episodes": 10, "eval_datetime": "2024-10-11T16:15:04.730153"}