My first model

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -130.75 +/- 14.35
+      value: -136.25 +/- 22.72
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16329f1ecec073e0ebd3b93d85f2aafa5a3963e241b62a6638025a6e0fe4dada
+oid sha256:51d463b9ee3b67d86ef576b862dfb99d0984adea359a7837fd7995bc09db76b0
 size 143955

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117187f12a33fb61e7054ee1705ef354971ef9d59294b5fc1dfada739218e970
-size 273995
+oid sha256:eac44b09f4ac332a8a866a0711366d846e0a2c8c327bfef8b1ee98bc29487e5f
+size 201490

results.json

@@ -1 +1 @@
-{"mean_reward": -130.75245352408092, "std_reward": 14.34904018867286, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T00:27:20.634288"}
+{"mean_reward": -136.24946929019498, "std_reward": 22.721262368683046, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-12T00:28:33.397559"}