Upload PPO LunarLander-v2 trained agent2

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 308.13 +/- 12.98
+      value: 293.55 +/- 23.47
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec1115a5516b033df9d9a2b98c6a65cbdf2c98357d254700ffbc70a348b9a947
+oid sha256:6b170f73ec279c857bf5ce134b1498b19670a36b6591779f05a061f27cd030be
 size 146632

results.json

@@ -1 +1 @@
-{"mean_reward": 308.1300138, "std_reward": 12.983414360156177, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-17T07:09:01.897562"}
+{"mean_reward": 293.5535108, "std_reward": 23.474598154478073, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-09-17T07:11:47.427367"}