# Switching exploration through action subspaces

**URL:** <https://discuss.ray.io/t/switching-exploration-through-action-subspaces/8163>\
**Category:** RLlib\
**Created:** [November 7, 2022, 2:10pm UTC](https://discuss.ray.io/t/switching-exploration-through-action-subspaces/8163 "2022-11-07T14:10:22Z")\
**Posts on this page:** 1\
**Showing post:** 11

<div class="post-metadata">

**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, 7:42pm UTC](https://discuss.ray.io/t/switching-exploration-through-action-subspaces/8163/11 "2022-11-11T19:42:10Z")

</div>

Thanks for a clear explanation @mannyv . I am able to implement exploration class that achieves the training I want for learner. Can you please look into my follow up question here

> [@Using different get\_exploration\_action logic pre and post training](https://discuss.ray.io/t/using-different-get-exploration-action-method-pre-and-post-training/8242):
>
> 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: @sv…

---

_[View the full topic](https://discuss.ray.io/t/switching-exploration-through-action-subspaces/8163)._