# Yet another question on RNN sequencing

**URL:** https://discuss.ray.io/t/yet-another-question-on-rnn-sequencing/4549
**Category:** RLlib
**Created:** [January 1, 2022, 11:42am UTC](https://discuss.ray.io/t/yet-another-question-on-rnn-sequencing/4549 "2022-01-01T11:42:53Z")
**Posts on this page:** 1
**Showing post:** 4

<div class="post-metadata">

### Author: ![mannyv](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/mannyv/32/606_2.png) [@mannyv](https://discuss.ray.io/u/mannyv)
#### Post date: [January 2, 2022, 4:49pm UTC](https://discuss.ray.io/t/yet-another-question-on-rnn-sequencing/4549/4 "2022-01-02T16:49:19Z")

</div>

Hi @mg64ve

There are 3 (sometimes 4) distinct phases that the model is called in.

Your debugging has revealed 2 of them.

These 3 are from the initialization phase. The y are taken from a dummy batch of all zeros. I ignore these unless they are generatimg an error.

```auto
torch.Size([32, 1, 2])
torch.Size([1, 1, 2])
torch.Size([4, 8, 2])

```

These are from the rollout phase when compute actions is called to sanple new trajectories from the environment. Your config has 20 envs per worker each of which is taking 1 step.

```auto
torch.Size([20, 1, 2])
torch.Size([20, 1, 2])

```

After you collect 4000 steps the training phase will run. You have not reported that phase but when you hit it it will have shape [num\_episodes,max\_seq,2]. The max\_seq is dynamic by default so if you did not have an episode that lasted 20 steps then it will be shorter than that.

Happy New Year

* * *

> **[Manny is helping people do cool things with RL](https://www.buymeacoffee.com/mannyv)**
>
> Hey, so glad we got to connect. If you found my suggestions useful feel free to buy me a coffee!

---

_[View the full topic](https://discuss.ray.io/t/yet-another-question-on-rnn-sequencing/4549)._