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 +/- 201.00
+      value: 580.00 +/- 208.81
       name: mean_reward
       verified: false
 ---

ppo-MultiInputPolicy-CustomSnake-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6866b7708502d06481ce915058ceb728ee6e02949fcb9cc82ca71330d0dab9c6
+oid sha256:6a54bfdeac811480390ec54c692a829afc8dafb57c0cd017b2512819e4a8563a
 size 235088

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95ca1d18388db9c5f1f49113a98db7cedf3fc91535b513d825e2caa4cabbe7dc
-size 143072
+oid sha256:d13683c1c874b6779283841fce1a6d5528e8a440af426db0cbdb39bec6be064c
+size 305053

results.json

@@ -1 +1 @@
-{"mean_reward": 640.0, "std_reward": 200.9975124224178, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-07T15:06:04.739382"}
+{"mean_reward": 580.0, "std_reward": 208.806130178211, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2024-05-07T15:07:10.818701"}