Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: -1795.55 +/- 694.77
+      value: -1485.87 +/- 550.26
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3df1ca5a5c41795eea037087a7b48b815ce49f434e60ddd2e1eed3c6debcffa
+oid sha256:bfcdcccf4bbca207e814c62ef6bdaaf671db430d6076f92db689592f3e321771
 size 147932

results.json

@@ -1 +1 @@
-{"mean_reward": -1795.5484987999996, "std_reward": 694.765188452555, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-07T23:28:23.099792"}
+{"mean_reward": -1485.8681354806758, "std_reward": 550.2593678465073, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-03-07T23:29:32.060248"}