Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 257.58 +/- 21.30
+      value: 254.44 +/- 16.08
       name: mean_reward
       verified: false
 ---
@@ -24,3 +24,14 @@ model-index:
 # **PPO** Agent playing **LunarLander-v2**
 This is a trained model of a **PPO** agent playing **LunarLander-v2**
 using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
+
+## Usage (with Stable-baselines3)
+TODO: Add your code
+
+
+```python
+from stable_baselines3 import ...
+from huggingface_sb3 import load_from_hub
+
+...
+```

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41eb7539a242425b0f74cabd13e23e91d040331a60dd6b76d177ec8fdce2f4a8
+oid sha256:fe211ba2c630574d841af5d449964dd061cba72c3464ff5de52da978edbdbbb3
 size 146755

results.json

@@ -1 +1 @@
-{"mean_reward": 257.58487932182044, "std_reward": 21.304365575486106, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-13T10:09:46.176356"}
+{"mean_reward": 254.44156512764093, "std_reward": 16.076330889360477, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-05-13T10:19:36.874392"}