Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 286.86 +/- 16.85
+      value: 290.77 +/- 11.07
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:336627851cfd2f71f7235bd3f9cadeaf705fd9b1cd262e4e3029fe94f1c31cfb
+oid sha256:de2c7db0dcbb68af791cfd63b59da6b5d36a355a1a845dae6c7315f039a7fd6f
 size 145900

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:215e64dfd77cfaa99509dd025c497d734c3b4d0d06f4b81fdc97e65bc272cc86
-size 195001
+oid sha256:a1f6e2f1dd033d9b4af092e9c6bd9cd59a43186362f313d0cf17713d1145ac5a
+size 197130

results.json

@@ -1 +1 @@
-{"mean_reward": 286.86356225425817, "std_reward": 16.851408597981305, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T16:48:30.864872"}
+{"mean_reward": 290.77336913942827, "std_reward": 11.071066229224982, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T16:49:28.491758"}