# Right way to get output from an HTM system

**URL:** <https://discourse.numenta.org/t/right-way-to-get-output-from-an-htm-system/8881>\
**Category:** Getting Started\
**Tags:** spatial-pooling\
**Created:** [August 19, 2021, 10:58am UTC](https://discourse.numenta.org/t/right-way-to-get-output-from-an-htm-system/8881 "2021-08-19T10:58:36Z")\
**Posts on this page:** 1\
**Showing post:** 7

<div class="post-metadata">

**Author:** ![mraptor](https://yyz2.discourse-cdn.com/flex030/user_avatar/discourse.numenta.org/mraptor/32/4469_2.png) [@mraptor](https://discourse.numenta.org/u/mraptor)\
**Post date:** [August 20, 2021, 6:19pm UTC](https://discourse.numenta.org/t/right-way-to-get-output-from-an-htm-system/8881/7 "2021-08-20T18:19:14Z")

</div>

> [@LukeTPeterson](#):
>
> Here is a different formulation of the question: **What is the architecture of the simplest HTM-based system capable of taking an action?**

TBT does not have RL yet.

My current idea is :  
TM-like structure.  
Dendrite Input : State  
FF : ??  
Prediction: use Action SDR (the predicted SDR == actual Acion SDR bits) and a REWARD to figure out which dendrites to boost from t-1

The update rule has to keep the last step Active neurons and dendrites /in a buffer/, so that you can do Q-value calc like you do in RL.

Sort of like Ensemble RL that predict active bits of SDR which should match Action-SDR

Then pass this Action to CC. Sense is State.

So what is left is how you represent and apply a GOAL.

---

_[View the full topic](https://discourse.numenta.org/t/right-way-to-get-output-from-an-htm-system/8881)._