PPO Model v2

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 289.65 +/- 21.34
+      value: 286.05 +/- 23.11
       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:a72ca2d1ab13cbeea5db607779b97b5525d028bc0cb762cb79976813c01a258e
+oid sha256:c9d971eb6378495165115013fb091e60784357c974012821d3907819a7ec4cb1
 size 48111

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c3a48be6e3ac2e2f05ed8ff44c43c8b869ad6bbded159b268221fb4d3dd2dc
-size 178989
+oid sha256:3301215fea31bdc6f81a4ace7ddd8a091ec6128b68d6a4429ec1bba18c316c68
+size 182995

results.json

@@ -1 +1 @@
-{"mean_reward": 289.65316468618937, "std_reward": 21.33569383877523, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T21:35:59.176125"}
+{"mean_reward": 286.05366386984394, "std_reward": 23.11047313481399, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-06T21:37:29.262261"}