10m steps

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 285.92 +/- 20.13
+      value: 289.26 +/- 18.33
       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:eb76d805697923c18abe016882e2d3e77f485b51c6cefab4b436ba73a11c2cda
+oid sha256:5f62bd87ad85ad89f40332f24cd58de1b3f9934a5c9bec13c7bf21b3ec5f2a79
 size 144158

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31924627e8cf7e02b1f0453a0c3894fe6a9ccc81730dc5954b40033eda8acf24
-size 187189
+oid sha256:2cd0321159fc11c7278946af520f788f29db1a14885773aba1159df2f6ce2d44
+size 199704

results.json

@@ -1 +1 @@
-{"mean_reward": 285.9203131038186, "std_reward": 20.128335678563207, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T01:24:32.110316"}
+{"mean_reward": 289.2563382642683, "std_reward": 18.329229668436163, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T01:33:50.244956"}