Upload PPO PongNoFrameskip-v4 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: PongNoFrameskip-v4
     metrics:
     - type: mean_reward
-      value: -2.50 +/- 2.94
+      value: 2.40 +/- 3.17
       name: mean_reward
       verified: false
 ---

ppo-PongNoFrameskip-v4.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee137fa4601127e82bdae9a1611058515724144525dec1cbf2a563d2ac5d8dbb
-size 20258362
+oid sha256:96771cd9a8946289426b740deede60b518934fed39cf8c4c726661aaf596a969
+size 20588875

ppo-PongNoFrameskip-v4/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3f55c7aa733a1a60c0ac17e781a65f5169ac5738e6aca7e76ad3c38c51c0fe
-size 13462634
+oid sha256:fd96fa55315a9faacba98d0792977b798a74e9ad40123e47a8047c5eb59f0b3d
+size 13511786

ppo-PongNoFrameskip-v4/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f9e1abc176928752258a185946d4917c4c1639a4ed8566668dfee0a63665b4
-size 6733682
+oid sha256:0d5483d4f0a81457afbae0516464a1af357d24e0888af8a42395158ecf46726d
+size 6758258

results.json

@@ -1 +1 @@
-{"mean_reward": -2.5, "std_reward": 2.9410882339705484, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-11T16:16:02.006233"}
+{"mean_reward": 2.4, "std_reward": 3.168595903550972, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2024-08-11T16:45:49.745681"}