Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 267.63 +/- 17.97
+      value: 246.19 +/- 74.68
       name: mean_reward
     task:
       type: reinforcement-learning

ppo_lunar_lander_v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca0b04c4ea5602cb2d3c3133f6c48ba46007aa7fd64dafa093182f094fce9c4
+oid sha256:839920febd44b23b08ab887e0d2b9ff4fe8783ff67ff49b944fb7b60e8df8de9
 size 144039

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de36e05423918740d7b70a6f31b75ff7522ce941d4e7b391758f91cf627836c5
-size 188906
+oid sha256:5f05ea100be4e13f3d9795a8e99ffbf3416c408b37e5e3646426bf8b9d73af94
+size 201234

results.json

@@ -1 +1 @@
-{"mean_reward": 267.62725564017654, "std_reward": 17.972465266422606, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T05:54:49.116799"}
+{"mean_reward": 246.19376895325945, "std_reward": 74.6805519635767, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-07T05:58:04.081822"}