Upload PPO LunarLander-v2 trained agent

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+replay.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 247.69 +/- 24.54
+      value: 238.45 +/- 42.46
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c4a2186f72eec641468b73e19f5c3b51d87c6b09f543500645dc7b2ce3c1521
+oid sha256:2ac2b18770dbf139e104560f4cdf1788d596b214d3d115497a7c47affb625782
 size 148120

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4572df3cd2bdad659dfc9c3b2abf96083e7e213ac1b0c36361335bc2fe7c585
+size 183626

results.json

@@ -1 +1 @@
-{"mean_reward": 247.68991929999999, "std_reward": 24.543712295839313, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-07T08:57:41.453296"}
+{"mean_reward": 238.4513311, "std_reward": 42.45683402889388, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-07T08:57:57.527038"}