Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -54.22 +/- 69.93
+      value: -156.37 +/- 166.00
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c591c10649d6ec427941fda06512c88af026ef1f011f871eb2f226a16b52a0
+oid sha256:58918abd93a2c614f65cc3e3f3f0090de5aa9ccd47c6a73d5977afcdf64efcb4
 size 147261

results.json

@@ -1 +1 @@
-{"mean_reward": -54.21709790000001, "std_reward": 69.93100428719384, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-04T07:35:26.890565"}
+{"mean_reward": -156.3670454807172, "std_reward": 165.99697085115258, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-03-04T07:36:58.676904"}