# Custom environment with continuous state and action spaces

**URL:** <https://discourse.julialang.org/t/custom-environment-with-continuous-state-and-action-spaces/105595>\
**Category:** Machine Learning\
**Tags:** package\
**Created:** [October 30, 2023, 7:58pm UTC](https://discourse.julialang.org/t/custom-environment-with-continuous-state-and-action-spaces/105595 "2023-10-30T19:58:58Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![hicham\_henna](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/hicham_henna/32/202824_2.png) [@hicham\_henna](https://discourse.julialang.org/u/hicham_henna)\
**Post date:** [October 30, 2023, 7:58pm UTC](https://discourse.julialang.org/t/custom-environment-with-continuous-state-and-action-spaces/105595/1 "2023-10-30T19:58:58Z")

</div>

how to implement a custom environment with continuous state and action spaces in the reinforcement learning framework under Julia? for example, to control the attitude of satellite we need the definition of: (i) markovian state as 7 dimensional real vector(4 for quaternion and 3 for angular rate), and (ii) the 3D action space as it is a 3-axis stabilisation problem.