Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 267.69 +/- 21.79
+      value: 273.21 +/- 16.30
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc17a44079a079dfdd4fe7d9c1ad0a83560870766ae16f4e01377e8f02f15575
+oid sha256:3a0c9b20d5ab02f384cbb10059e91b77d23934b29ebd1f61adc8d13c984a6e44
 size 148120

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2f00df47811bbc397ba646b8c45a68d0e03a70c575fb44eb283797afd1febc3
-size 158042
+oid sha256:5ba50c27d8ff407c6595cc901636227428a3da0f9aca951062ded3986ed5e41b
+size 167536

results.json

@@ -1 +1 @@
-{"mean_reward": 267.68665120000003, "std_reward": 21.7918773586233, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-04T20:35:51.982494"}
+{"mean_reward": 273.2085935, "std_reward": 16.295759005412247, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-04T20:39:16.783647"}