Reinforce-PongPolGrad-2200 training episodes

README.md

@@ -16,7 +16,7 @@ model-index:
       type: CartPole-v1
     metrics:
     - type: mean_reward
-      value: 9.38 +/- 0.62
+      value: 9.46 +/- 0.75
       name: mean_reward
       verified: false
 ---

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615a8cd629d0ac2456597c0f3938820d8b37931db4c8eb3823cccd49436ee0b3
-size 3197
+oid sha256:938bd1c3e2735fe0683024a311a264ce01cdedf14a0759bcee16c7938b77578c
+size 3390

results.json

@@ -1 +1 @@
-{"env_id": "CartPole-v1", "mean_reward": 9.384615384615385, "n_evaluation_episodes": 13, "eval_datetime": "2022-08-28T17:35:31.638934"}
+{"env_id": "CartPole-v1", "mean_reward": 9.461538461538462, "n_evaluation_episodes": 13, "eval_datetime": "2022-08-28T17:37:10.586053"}