Tuned PPO agent trained on LunarLander-v2 (1 million timesteps)

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 282.31 +/- 20.05
+      value: 281.93 +/- 16.59
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f4a3e7eb0602b3dff6983b132da8e176226c6b56d67695143d74bbcf0e973d
+oid sha256:3adfb64cbaa43e56a1cc3b69fe7d88f53f5b903fd7f80814298716ee45b12821
 size 149969

results.json

@@ -1 +1 @@
-{"mean_reward": 282.3083673, "std_reward": 20.045812325246818, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-26T13:40:40.058680"}
+{"mean_reward": 281.9335196, "std_reward": 16.589408548428363, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-02-26T13:42:59.084369"}