Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -125.17 +/- 14.09
+      value: -123.87 +/- 19.22
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b91307ebf8139daccd4ef551d28582a619b42b1d7fc0f2dc61249129bed7bf6
+oid sha256:f3c254fef95fbbc800b6bf03ba9ce97cf5b098d76139209ae665727bc855bb5b
 size 140922

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79777bfb3a8ccaec98fa9837c0f9fcf78142fc993e605371fe8aecd437e013ef
+size 172760

results.json

@@ -1 +1 @@
-{"mean_reward": -125.173321740143, "std_reward": 14.094646454147178, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T20:26:50.806885"}
+{"mean_reward": -123.8688810897991, "std_reward": 19.21930683731547, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T22:52:29.860525"}