Upload PPO LunarLander-v2 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 194.42 +/- 64.10
+      value: 122.26 +/- 112.02
       name: mean_reward
     task:
       type: reinforcement-learning

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6703843a6609d61e74de9be6b253a64e9876ed24238b4620d5a437f915a20bdd
+oid sha256:3f89ebd44697182084281aed408c68501230ebc37669ef658c462191f8e20ba9
 size 143976

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d4b04c2c788d845ef8871a4759b3373f7dbee00e3464cd96790683a67ece1f2
-size 199984
+oid sha256:6d12ed7e179f723ec8ffcf55c95603aaf80a14368dfd31fd22990fec59901010
+size 249446

results.json

@@ -1 +1 @@
-{"mean_reward": 194.42486648672002, "std_reward": 64.10277112110784, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T18:17:46.055738"}
+{"mean_reward": 122.26400666548243, "std_reward": 112.01736296543932, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-08T18:21:53.781479"}