Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 213.17 +/- 16.03
+      value: 206.68 +/- 22.40
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3abc8d996bfa975e93f4af26fe5671812f182cae86867397bc99fb3b599f8e1e
+oid sha256:a3cfab3aaee037b829b5db79f4534ddec06b1817cfd76fad868898c6c81ac9c9
 size 144044

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:292b7baaab6c0b8fbdf1902a2242dbfe3ad8dfb0f9f2b0d1bd604aad176c1950
-size 263390
+oid sha256:747c0931f5dc5c9ed01fd57fa2befbe164e0ce04c3e2a287ea4dd073f96339a8
+size 261818

results.json

@@ -1 +1 @@
-{"mean_reward": 213.17044689567305, "std_reward": 16.030162870278033, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T03:59:58.423321"}
+{"mean_reward": 206.67538789485883, "std_reward": 22.40344591989021, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T04:28:01.378123"}