# Using different get\_exploration\_action logic pre and post training **URL:** \ **Category:** RLlib\ **Created:** [November 11, 2022, 7:37pm UTC](https://discuss.ray.io/t/using-different-get-exploration-action-logic-pre-and-post-training/8242 "2022-11-11T19:37:43Z")\ **Posts on this page:** 2\ **Page:** 1
**Author:** ![Saurabh\_Arora](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/saurabh_arora/32/1012_2.png) [@Saurabh\_Arora](https://discuss.ray.io/u/Saurabh_Arora)\ **Post date:** [November 11, 2022, 7:37pm UTC](https://discuss.ray.io/t/using-different-get-exploration-action-logic-pre-and-post-training/8242/1 "2022-11-11T19:37:43Z")
Hey team , I have created a custom exploration class for problem I am trying to solve. I want to use two different get\_exploration\_action methods for following two parts of my code: - PPO training - compute\_action during simulation of episodes from learned policy post training. Is there a way to - modify config[“exploration\_config”][“type”] after training, or - add a custom argument for call to get\_exploration\_action? If neither, Can you please suggest a way to implement such a set up? cc: @sven1977 , @RickLan , @mannyv , @arturn , @RickDW , @rusu24edward , @gjoliver ---
**Author:** ![mannyv](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/mannyv/32/606_2.png) [@mannyv](https://discuss.ray.io/u/mannyv)\ **Post date:** [November 11, 2022, 10:18pm UTC](https://discuss.ray.io/t/using-different-get-exploration-action-logic-pre-and-post-training/8242/2 "2022-11-11T22:18:57Z")
@Saurabh_Arora, I have not tried it with 2.x but I would think you could just instantiate a new algorithm policy with the updated config that changes the exploration type. That would not work for one of the exploration types that trains a model l (Random Encoder and Curiosity) because the checkpoint won’t be able to match up weights and would error out but most explorations don’t do that.