Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 296.85 +/- 19.86
+      value: 294.60 +/- 19.92
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4314568843645ad8cf748f40f2feafa842cd0646d688a75a3c109525069ee8fd
+oid sha256:be8bee32da08c070ad5d3092e3f87b666d0b1ae510aa6404ccf8bdb274652903
 size 145900

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee3d0ac1775f09662c7d6ef43bbeb79807d9e76aadb4094540723e609a2384a4
-size 202696
+oid sha256:d132435bfdf11164317442226c5d08b9127aad959538846c3f6d5a9d23045fbd
+size 195459

results.json

@@ -1 +1 @@
-{"mean_reward": 296.8463028150729, "std_reward": 19.86258426961982, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T16:45:34.884917"}
+{"mean_reward": 294.6001049229093, "std_reward": 19.920547442049582, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T16:47:12.615957"}