Upload PPO LunarLander-v2 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CarRacing-v0
     metrics:
     - type: mean_reward
-      value: -54.33 +/- 5.70
+      value: -24.75 +/- 10.15
       name: mean_reward
       verified: false
 ---

ppo-CarRacing-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50460e1e6af47b3ddaaba77164b445630ccf1fe7d0b1bd271311c6a84248c853
-size 42894740
+oid sha256:c132833755c8f7e7756c1798a3864ba83f8b14addf43096312191287617a6b7a
+size 42898552

ppo-CarRacing-v1/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf6cd5c8f7a91bdb13626007a7c7c3e9474c8d7ae6c0c6d27988ba8d46354563
+oid sha256:ae6f65f7f13efa0aa36c9069a6a570b4a71f6c4b441f1a86e08f673aad2c7896
 size 28391536

ppo-CarRacing-v1/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e81fb41d55dbaa22825415aaef1e40102668d4adeac726568319a45c609e52f1
+oid sha256:4a723f2ce48a713a172a7d1886a74f93e210bbace507e465970c77dd70589c03
 size 14195134

results.json

@@ -1 +1 @@
-{"mean_reward": -54.330694230645896, "std_reward": 5.699226950966611, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-29T03:44:47.423355"}
+{"mean_reward": -24.75354374498129, "std_reward": 10.148067672490948, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-01-29T04:18:54.240027"}