Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: -28.57 +/- 168.66
+      value: 108.15 +/- 153.65
       name: mean_reward
     task:
       type: reinforcement-learning

chika2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5688d77bcae891b7aee69e365dfd582b123c4e1c7cd0209da07b67cfbec9b263
+oid sha256:fadd8bf8101aae8af1d031e8d539488fd3638b24cb4071adac5b3d49372cec3a
 size 144070

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e30957b0eb27528d4e03517ac8045babedbab341db4d3701a089b419178148b
-size 269159
+oid sha256:da5ada9a82394919cbb390d211a612c70324b1421ee31b8aadc8d141d572f699
+size 279509

results.json

@@ -1 +1 @@
-{"mean_reward": -28.568661301632424, "std_reward": 168.66374499792167, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-18T19:09:20.393416"}
+{"mean_reward": 108.15118382690062, "std_reward": 153.64979730905742, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-18T19:12:02.501876"}