PPO Model

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 272.06 +/- 21.36
+      value: 274.76 +/- 21.93
       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:b5e6bf8e676b8048e34c94354939f01c545c7ad231607d0115474deb35b283d7
+oid sha256:afd1e97adce6f6a72da58f6fb021209bdaae0ca6d5949dcc21d79831687382ce
 size 146069

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9314e95ac430dea11b5bc1f8fdb71559c9e357f2491271e1148fdf2a6a18c9a
-size 199054
+oid sha256:5bf2042e36343e6d72aac2afce59a892d4fe73a2f078c850cc6bf779509ab833
+size 177362

results.json

@@ -1 +1 @@
-{"mean_reward": 272.06433075821144, "std_reward": 21.35560781750557, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T10:42:06.053298"}
+{"mean_reward": 274.76415492379573, "std_reward": 21.926303266842545, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T10:52:46.428543"}