Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 156.20 +/- 85.34
+      value: 149.85 +/- 82.42
       name: mean_reward
     task:
       type: reinforcement-learning
@@ -22,6 +22,7 @@ model-index:
 
 
 
+
   # **PPO** Agent playing **LunarLander-v2**
   This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
   

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253e46704382db1844bff1b4992ff94713bc2ad0c7a9520fc4ff0f0ec338b207
+oid sha256:5164de470232533c05f95dfb978b9d257705544263e852b85237166629467391
 size 143470

results.json

@@ -1 +1 @@
-{"mean_reward": 156.20404110377777, "std_reward": 85.34149716378923, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T15:20:09.300409"}
+{"mean_reward": 149.85388098018012, "std_reward": 82.41923265347738, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T15:22:13.726086"}