Initial commit

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 253.34 +/- 28.79
+      value: 222.50 +/- 86.59
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24d385e2618f3e394a5ffe30b8fbfbd78f47530956ec4634a31651a08b1d24f5
+oid sha256:1d61a382483ac919de37b8c7e7e7e1081457bbd72580f1df751a523ed2affd79
 size 143879

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b960b897794342667eb93b655f6d1eb63c609b02023a9e833b7ae7e923ddda63
-size 321611
+oid sha256:f4bf5ad061439fb80349493e1aed95e9e4a1fd965f3d2ea9ad2afd42022f1b58
+size 288314

results.json

@@ -1 +1 @@
-{"mean_reward": 253.34440319969568, "std_reward": 28.789523694862158, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T14:14:23.511017"}
+{"mean_reward": 222.49668897624852, "std_reward": 86.5943554005973, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-11T14:15:28.063553"}