Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 2.43 +/- 152.47
+      value: 28.44 +/- 165.66
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54aa70a6070245f402bc1cfb5ffec285bde188fa771374301cf9a3c99e50b712
+oid sha256:0c33fc4a8534858382a9b211e767a2911da7ee84f06ac5ae5ccf864b8ced6692
 size 147236

results.json

@@ -1 +1 @@
-{"mean_reward": 2.429806950472795, "std_reward": 152.4713214255308, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-05T13:16:51.083316"}
+{"mean_reward": 28.436894584635958, "std_reward": 165.6600458639743, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-08-05T13:21:33.683263"}