# Prediction outside outside action space during inference

**URL:** <https://discuss.ray.io/t/prediction-outside-outside-action-space-during-inference/14051>\
**Category:** Uncategorized\
**Created:** [March 18, 2024, 1:25pm UTC](https://discuss.ray.io/t/prediction-outside-outside-action-space-during-inference/14051 "2024-03-18T13:25:09Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![riles](https://avatars.discourse-cdn.com/v4/letter/r/ecc23a/32.png) [@riles](https://discuss.ray.io/u/riles)\
**Post date:** [March 18, 2024, 1:25pm UTC](https://discuss.ray.io/t/prediction-outside-outside-action-space-during-inference/14051/1 "2024-03-18T13:25:09Z")

</div>

Hello,

I’m running PPO with custom env. The training is running perfectly, I checked it predicted action within the action space.

I save a checkpoint every iteration. But when I load it, the action predicted by the loaded policy using policy.from\_checkpoint are ranging from -1 to 1 where the action space should be between 0-30.

is there any postprocessing i’m missing ?

help please