Upload ppo MultiInputPolicy CustomSnake-v0 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CustomSnake-v0
     metrics:
     - type: mean_reward
-      value: 600.00 +/- 322.49
+      value: 510.00 +/- 341.91
       name: mean_reward
       verified: false
 ---

ppo-MultiInputPolicy-CustomSnake-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6785a0880ac17342a9695845e134179493faf7306edf945536d7d1739528ac57
+oid sha256:698102d99ed4b5f0d3f14b5e0575c0bbf7ee6fe6c2d20ff7abef003318d7f636
 size 235088

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:333cd86f58f95f6a9f6400de23005f1b7872ad33668ede77279af39122c37b72
-size 2121633
+oid sha256:3a4e06e630b542da6b3653031e14c5b094ed0622f4525e61d8fef09b8c5f6a8a
+size 1911500

results.json

@@ -1 +1 @@
-{"mean_reward": 600.0, "std_reward": 322.49030993194197, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-07T00:07:53.761954"}
+{"mean_reward": 510.0, "std_reward": 341.9064199455752, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-07T00:20:29.380023"}