Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 36.25 +/- 106.75
+      value: -33.74 +/- 126.65
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53feb9a12dfb1454f5af87378257252ee7bb4082dd05a98a946cfded562002f6
+oid sha256:ef378c699b60cd60dd7f97d7e99f390ad914504ee53fe9e6367efceb3d2ac671
 size 147512

results.json

@@ -1 +1 @@
-{"mean_reward": 36.246716799999994, "std_reward": 106.753403476096, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-15T04:14:57.915241"}
+{"mean_reward": -33.735651100000005, "std_reward": 126.64679533217951, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-04-15T04:17:42.318228"}