ppo_FrozenLake-v1 trained agent

README.md

@@ -10,7 +10,7 @@ model-index:
   results:
   - metrics:
     - type: mean_reward
-      value: 0.70 +/- 0.46
+      value: 0.40 +/- 0.49
       name: mean_reward
     task:
       type: reinforcement-learning

ppo_'FrozenLake-v1.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a666554cb6f48664a8a266e89e3e96f8f69235cbdf6a0b7fb173f8c88018d6d1
+oid sha256:401dd65b2838cdd4e0d13c7098b72b197e04783199db9fef323ae2786be80d59
 size 153592

results.json

@@ -1 +1 @@
-{"mean_reward": 0.7, "std_reward": 0.45825756949558394, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-14T16:16:55.165436"}
+{"mean_reward": 0.4, "std_reward": 0.4898979485566356, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2022-05-14T16:22:49.502646"}