Upload PPO LunarLander-v2 trained agent, 1st try, 1000000 steps

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 271.34 +/- 24.37
+      value: 292.95 +/- 19.46
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2b.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65e5dd72846d1dd8bfa239a470a54ed5dd81c884304d12870d59c3b37d8477f7
+oid sha256:39129e9ffb3f39f6fda67ad4b2193c1ebfcefcc24642758227e9be4015d34b4f
 size 147637

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db18d7a69a502dcb28cfab038abfb74bbbffc68be49599dc0ac088cbbe55fefe
-size 185300
+oid sha256:0213c7a9031bc96b158293c783b2ef961a3b0e53b337b88bfe223f8a4c3ad621
+size 188793

results.json

@@ -1 +1 @@
-{"mean_reward": 271.3413132432498, "std_reward": 24.36661590399868, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T04:20:05.843005"}
+{"mean_reward": 292.9529173647535, "std_reward": 19.45802323841769, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T04:20:42.334688"}