Upload PPO PongNoFrameskip-v4 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PongNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: 2.40 +/- 3.17
+      value: 10.80 +/- 4.14
       name: mean_reward
       verified: false
 ---

ppo-PongNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96771cd9a8946289426b740deede60b518934fed39cf8c4c726661aaf596a969
-size 20588875
+oid sha256:abe11bdee372d8b4989ee3d5a120755141709b66622b6673f36888fcfd350d8c
+size 20903272

ppo-PongNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd96fa55315a9faacba98d0792977b798a74e9ad40123e47a8047c5eb59f0b3d
-size 13511786
+oid sha256:874fffa87bc51b927b368a60a930a6fa29a0277bf8fc2037483247a125a10a52
+size 13544554

ppo-PongNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5483d4f0a81457afbae0516464a1af357d24e0888af8a42395158ecf46726d
-size 6758258
+oid sha256:149431aa51173b8cef17ac0a2796bbd28f3393a5208e40ec8ef05ab5869080c7
+size 6774642

results.json

@@ -1 +1 @@
-{"mean_reward": 2.4, "std_reward": 3.168595903550972, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-11T16:45:49.745681"}
+{"mean_reward": 10.8, "std_reward": 4.1424630354415966, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-11T18:10:22.881675"}