Upload ppo MultiInputPolicy CustomSnake-v0 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CustomSnake-v0
     metrics:
     - type: mean_reward
-      value: 580.00 +/- 295.97
+      value: 660.00 +/- 195.96
       name: mean_reward
       verified: false
 ---

ppo-MultiInputPolicy-CustomSnake-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:545a05ba7dc85446b38bbff24843814aa9da91361c1cf7abd46a79de84497be5
+oid sha256:217d85d4982d613fde51fbbb45bdc89884dfce6a55ed999628bc1fe2516d5ffe
 size 235088

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ee3b054fd22e205255bf041bd9f80ee58ce972371fcd829f8cbce449197252
-size 311342
+oid sha256:38bd7594f9f8ab20f3eb93bad773e49326dbf2be099704c91582d033b8ab8192
+size 330599

results.json

@@ -1 +1 @@
-{"mean_reward": 580.0, "std_reward": 295.9729717389748, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-07T15:08:44.520620"}
+{"mean_reward": 660.0, "std_reward": 195.95917942265424, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-07T15:09:13.179075"}