# Use LSTM model for policy gradient multi-agent with different recurrent hidden states per agent

**URL:** <https://discuss.ray.io/t/use-lstm-model-for-policy-gradient-multi-agent-with-different-recurrent-hidden-states-per-agent/15385>\
**Category:** Configure Algorithm, Training, Evaluation, Scaling\
**Created:** [July 30, 2024, 2:43am UTC](https://discuss.ray.io/t/use-lstm-model-for-policy-gradient-multi-agent-with-different-recurrent-hidden-states-per-agent/15385 "2024-07-30T02:43:10Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![kimhyun1018](https://avatars.discourse-cdn.com/v4/letter/k/59ef9b/32.png) [@kimhyun1018](https://discuss.ray.io/u/kimhyun1018)\
**Post date:** [October 21, 2025, 1:53am UTC](https://discuss.ray.io/t/use-lstm-model-for-policy-gradient-multi-agent-with-different-recurrent-hidden-states-per-agent/15385/2 "2025-10-21T01:53:36Z")

</div>

Is there any update on this? I’m facing a similar issue [too](https://discuss.ray.io/t/multi-agent-ppo-rollout-stalls-duplicate-agent-at-same-env-t-assertion-under-connector-v2-ray-2-49-2/23253/4).

---

_[View the full topic](https://discuss.ray.io/t/use-lstm-model-for-policy-gradient-multi-agent-with-different-recurrent-hidden-states-per-agent/15385)._