Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 191.06 +/- 84.30
+      value: 195.82 +/- 82.45
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83c4cc300222814d556f408ff82dee3d8051940ff45ea9a5481cf5f73c37c358
+oid sha256:02b6e22bf118a5cff4d038d4f5521ae7fe8f20d6f5d7603ab4c7e7d54bf28af3
 size 144144

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4011d030f5561b74cb37e72efe4c02f3dc481343fa4ac6a50084b5f9e26d3ff3
-size 184781
+oid sha256:23cdd4175c98829b3fa570a459b8fc3478b7d1c01b9fc9078fbacd1ac34a4dcb
+size 198819

results.json

@@ -1 +1 @@
-{"mean_reward": 191.06361991420542, "std_reward": 84.29773979489588, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-22T11:28:35.695978"}
+{"mean_reward": 195.82223358926487, "std_reward": 82.45061354608238, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-06-22T11:49:48.416563"}