No changes, uploaded again to test some things

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 236.84 +/- 21.38
+      value: 261.77 +/- 24.46
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f7ba56a92e5153e1d311a6bb822d3b8fea9e8e2fb66983735f24461f10cd5ef
+oid sha256:ad1f80746c1c17e1c6d611f88159f3af59ce60cc891c4a76530408fcf6053e24
 size 144154

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e7b09778cd4a2de3cb98b6bed7a0dd10f860548bfea07e473b16d79d62fbc9b
-size 199775
+oid sha256:e52b10f20deabf069fb1a59b1b32b48c963ec9cae614e39f9aaa716b13d4d03b
+size 201815

results.json

@@ -1 +1 @@
-{"mean_reward": 236.84180527550865, "std_reward": 21.379262301641994, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-18T08:50:15.623467"}
+{"mean_reward": 261.7743272795781, "std_reward": 24.461782261740733, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-18T09:16:18.165294"}