Upload ppo MultiInputPolicy CustomSnake-v0 trained agent

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CustomSnake-v0
     metrics:
     - type: mean_reward
-      value: 640.00 +/- 297.32
+      value: 600.00 +/- 322.49
       name: mean_reward
       verified: false
 ---

ppo-MultiInputPolicy-CustomSnake-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4e581bdc05e6ae6678242dcf00e255345ed2af36dcb1999a32e08ee0d794e65
+oid sha256:6785a0880ac17342a9695845e134179493faf7306edf945536d7d1739528ac57
 size 235088

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a339a7a325e2063800f681a24344c26d886c6597bb1fa2ff14afd50330189f4f
-size 2223296
+oid sha256:333cd86f58f95f6a9f6400de23005f1b7872ad33668ede77279af39122c37b72
+size 2121633

results.json

@@ -1 +1 @@
-{"mean_reward": 640.0, "std_reward": 297.3213749463701, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-07T00:02:55.064572"}
+{"mean_reward": 600.0, "std_reward": 322.49030993194197, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-07T00:07:53.761954"}