1st try at PPO LunarLander following course code

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 246.24 +/- 22.68
+      value: 237.01 +/- 20.55
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ccc6941261da79993f11a2edd59098494df3221f40223e5d6f53c653584e139
+oid sha256:5db6979d8c83ee1d435e64941510094f79f06764e3b39b3b6e5f2c606bbea4de
 size 144182

replay.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2e53ea5e46c2141ee6e45319c374eeaba14b17bfa6bbe7f43607581a83f8bec
+size 248138

results.json

@@ -1 +1 @@
-{"mean_reward": 246.24176198134492, "std_reward": 22.675651928636633, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-17T21:35:05.777458"}
+{"mean_reward": 237.0091542429431, "std_reward": 20.553432497986854, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-17T21:37:51.691639"}