# Using random action policy with dict action space

**URL:** <https://discuss.ray.io/t/using-random-action-policy-with-dict-action-space/1678>\
**Category:** RLlib\
**Created:** [April 12, 2021, 6:30pm UTC](https://discuss.ray.io/t/using-random-action-policy-with-dict-action-space/1678 "2021-04-12T18:30:40Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![rusu24edward](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/rusu24edward/32/333_2.png) [@rusu24edward](https://discuss.ray.io/u/rusu24edward)\
**Post date:** [April 12, 2021, 6:30pm UTC](https://discuss.ray.io/t/using-random-action-policy-with-dict-action-space/1678/1 "2021-04-12T18:30:40Z")

</div>

Does anyone have any experience using the RandomPolicy in MARL environments where the action spaces are Dicts? I have run into a bug, which I have reported [here](https://github.com/ray-project/ray/issues/15252). I can work around this by hacking the rllib summarize function, but I wanted to just double check that I’m not setting up my env poorly.