Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: LunarLander-v2
     metrics:
     - type: mean_reward
-      value: 122.50 +/- 92.81
+      value: 175.95 +/- 65.75
       name: mean_reward
       verified: false
 ---

ppo-LunarLander-v2.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34cf2245108f15aa7d8897e528eb12a1c18d76c307b31ac34cf3427b4114fdc0
+oid sha256:fd3527cd973cf1bc7e55b4ea5acad89dd2e27031b2184319d00ac1ead26eb543
 size 147400

results.json

@@ -1 +1 @@
-{"mean_reward": 122.49884100000001, "std_reward": 92.81065531229827, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-18T12:48:00.221010"}
+{"mean_reward": 175.95480089348348, "std_reward": 65.74919707361329, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-18T12:50:54.212710"}