# Use Policy\_Trainer with TensorBoard

**URL:** https://discuss.ray.io/t/use-policy-trainer-with-tensorboard/4097
**Category:** RLlib
**Created:** [November 11, 2021, 12:38am UTC](https://discuss.ray.io/t/use-policy-trainer-with-tensorboard/4097 "2021-11-11T00:38:34Z")
**Posts on this page:** 1
**Showing post:** 25

<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: [November 12, 2021, 4:29pm UTC](https://discuss.ray.io/t/use-policy-trainer-with-tensorboard/4097/25 "2021-11-12T16:29:55Z")

</div>

@Denys_Ashikhin,

What version of ray are you currently using?

There is a bug with rnn sequencing in the latest release.

You can avoid it with these settings (assuming you are not trying to train with multi-gpu).

> [@TrajectoryTracking with RLLIB](https://discuss.ray.io/t/trajectorytracking-with-rllib/4094/10):
>
> @mg64ve You can a avoid the issue even in the current version by doing 2 things. Set the config[“simple\_optimizer”]=True Set sgd\_minibatch\_size \> max\_seq\_len

---

_[View the full topic](https://discuss.ray.io/t/use-policy-trainer-with-tensorboard/4097)._