Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 276.47 +/- 23.61
+      value: 265.86 +/- 11.09
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8427ac1a6f859cc80beedee4bae4889b5be3d4bf1faf06d0243c859b358c2c3c
+oid sha256:d3f2dc6be48748ed53c12200bf643ecfcaa09cb19f631a47ef7957a753eff277
 size 148003

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9f721e831f4f4020edd9612ed18f69a0f901801f32d7de261942e3596856746
-size 181200
+oid sha256:8df58ef59e0a28b3e28667d54c12a4e6b3951da601c8a8e60c72257feba8f489
+size 178364

results.json

@@ -1 +1 @@
-{"mean_reward": 276.47204209999995, "std_reward": 23.611777898794262, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-03T15:06:22.612704"}
+{"mean_reward": 265.8609502168422, "std_reward": 11.094538468108924, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2025-02-03T15:08:11.063416"}