# Coud we use continuous action space for parametric action spaces

**URL:** <https://discuss.ray.io/t/coud-we-use-continuous-action-space-for-parametric-action-spaces/2234>\
**Category:** RLlib\
**Created:** [May 21, 2021, 2:17am UTC](https://discuss.ray.io/t/coud-we-use-continuous-action-space-for-parametric-action-spaces/2234 "2021-05-21T02:17:42Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Shanchao\_Yang](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/shanchao_yang/32/803_2.png) [@Shanchao\_Yang](https://discuss.ray.io/u/Shanchao_Yang)\
**Post date:** [May 21, 2021, 2:17am UTC](https://discuss.ray.io/t/coud-we-use-continuous-action-space-for-parametric-action-spaces/2234/1 "2021-05-21T02:17:42Z")

</div>

Hi, though the example below shows the usage of parametric action space for cartpole, I would like to ask that if we can use continous action space to produce the parametric action.

Instead of letting the policy network produce a latent action vector `pi_t`, and we obtain the discrete action dist `dist = Discrete ( dot(pi_t, e) )`, where `e` is the available action embedding, can we consider the `pi_t` is sampled from a continuous action dist (like gaussian), and we then dot it with all action embeddings? But this would introduce two action distribution (gaussian + discrete). And I am not sure it is correct or not.

Thanks for any advice!

> <https://github.com/ray-project/ray/blob/master/rllib/examples/parametric_actions_cartpole.py>