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-v3
     metrics:
     - type: mean_reward
-      value: 292.22 +/- 12.63
+      value: 282.99 +/- 14.60
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v3.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3695e9437f633e2b402591d75bb521235f4cba95689fc0d610fc48524fae994
+oid sha256:29d3843da5a349c4839604853269ed62b57cda3294b098f9f94190d94cde530f
 size 149900

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b357db16c599d0a17f5bd5cb40aa3d9a326c6e013ef91b71010b2a175655d1b2
+size 147671

results.json

@@ -1 +1 @@
-{"mean_reward": 292.2202442116514, "std_reward": 12.627744762986366, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-01T03:24:34.201310"}
+{"mean_reward": 282.9903328113709, "std_reward": 14.5961801889725, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-12-01T03:40:19.355900"}