Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 292.58 +/- 13.09
+      value: 293.12 +/- 16.74
       name: mean_reward
     task:
       type: reinforcement-learning
@@ -22,3 +22,4 @@ model-index:
 
 
 
+

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:849948885d9feda9606b35717851923048211986c0864a57cdb9c52e8840a2e7
+oid sha256:4ab7fb60283cf7049e35220a6e259fffc34abdd2af95193afb115a055630b9a0
 size 143853

results.json

@@ -1 +1 @@
-{"mean_reward": 292.5825658600482, "std_reward": 13.094022228737604, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T17:08:48.850941"}
+{"mean_reward": 293.11987152138465, "std_reward": 16.73889138903816, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T17:12:07.385787"}