Upload ppo MultiInputPolicy CustomSnake-v0 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CustomSnake-v0
     metrics:
     - type: mean_reward
-      value: 680.00 +/- 381.58
+      value: 600.00 +/- 319.37
       name: mean_reward
       verified: false
 ---

ppo-MultiInputPolicy-CustomSnake-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec0f7d09b96734f312875794bf728c648ed2eb5bdf4f351825684aa1a19244fd
+oid sha256:f1636f8afd94579c79e4f572e2cb207f4320965a1f22649fb225a5c1b323e60d
 size 235088

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6802e564196a925310089a10cabb70e221cb26fd3aa5df07a7af290529c744f3
-size 296568
+oid sha256:eaf7988890c8e4ffe64d64c4fb5d49640913aba4a04313b1e243a46946dd275d
+size 300419

results.json

@@ -1 +1 @@
-{"mean_reward": 680.0, "std_reward": 381.57568056677826, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-07T15:07:47.144984"}
+{"mean_reward": 600.0, "std_reward": 319.37438845342626, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-07T15:08:13.982503"}