init

LunarLanderv2-ppo-1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd290bd7a409fe0791c9f1fb2ad631b876a7aed495900c62b395b4e28ff2e16b
+oid sha256:0be6e0ab80d4bde62ddf0382f21c985d1d5f633c9e681cc27c54f3a8f5ced418
 size 144106

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 209.13 +/- 75.73
+      value: 208.93 +/- 53.16
       name: mean_reward
     task:
       type: reinforcement-learning

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:124dbe5a8463165676b09b0b2197e532d3c9f4fb77b91a446f2aeb5d58d2693e
-size 236758
+oid sha256:76de31e5c6c17d00e22fce5638721c5919a088c2d727c5830df6e10a11213815
+size 232237

results.json

@@ -1 +1 @@
-{"mean_reward": 209.12598556842795, "std_reward": 75.72679350684315, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T09:23:30.573724"}
+{"mean_reward": 208.92766313042202, "std_reward": 53.162874557691595, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-10T09:26:28.299815"}