Upload ppo MultiInputPolicy CustomSnake-v0 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CustomSnake-v0
     metrics:
     - type: mean_reward
-      value: 510.00 +/- 341.91
+      value: 670.00 +/- 253.18
       name: mean_reward
       verified: false
 ---

ppo-MultiInputPolicy-CustomSnake-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:698102d99ed4b5f0d3f14b5e0575c0bbf7ee6fe6c2d20ff7abef003318d7f636
+oid sha256:a8260a00eb5567ebf9b13ad46580aa45f3c6141b4da6dbcd80277639e6d93da2
 size 235088

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a4e06e630b542da6b3653031e14c5b094ed0622f4525e61d8fef09b8c5f6a8a
-size 1911500
+oid sha256:e5b895b7596e84ee72a2dbb825d60970fca64da847d192b2cdf620e1ce42551e
+size 2178016

results.json

@@ -1 +1 @@
-{"mean_reward": 510.0, "std_reward": 341.9064199455752, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-07T00:20:29.380023"}
+{"mean_reward": 670.0, "std_reward": 253.17977802344325, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-07T00:24:15.630888"}