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: 232.91 +/- 17.70
+      value: 227.82 +/- 45.75
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8213e4e1cd6841360a82084ed50afce67bff4234d0d4bad1c169b1e72bf2f587
+oid sha256:f88cd29982715f320c867a5acce9d0b471be1240b1e4c305fe8265e5824d3db1
 size 150007

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e4f24eb1f4f16fe7ff6008b0759f36d98c1d369b9db8213de44d47e7a20a062
+size 171186

results.json

@@ -1 +1 @@
-{"mean_reward": 232.91162073130917, "std_reward": 17.699788118296166, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-18T16:36:29.755269"}
+{"mean_reward": 227.8151113270946, "std_reward": 45.753736748641465, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2026-04-18T16:45:32.458774"}