# What happens when you pass a custom model to an actor-critic method

**URL:** <https://discuss.ray.io/t/what-happens-when-you-pass-a-custom-model-to-an-actor-critic-method/5339>\
**Category:** RLlib\
**Created:** [March 8, 2022, 11:48am UTC](https://discuss.ray.io/t/what-happens-when-you-pass-a-custom-model-to-an-actor-critic-method/5339 "2022-03-08T11:48:33Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![carlorop](https://avatars.discourse-cdn.com/v4/letter/c/b19c9b/32.png) [@carlorop](https://discuss.ray.io/u/carlorop)\
**Post date:** [March 8, 2022, 11:48am UTC](https://discuss.ray.io/t/what-happens-when-you-pass-a-custom-model-to-an-actor-critic-method/5339/1 "2022-03-08T11:48:34Z")

</div>

Good morning. I want to use a custom neural network for TD3. In the documentation ( [RLlib Models, Preprocessors, and Action Distributions — Ray v1.10.0](https://docs.ray.io/en/latest/rllib-models.html)) I have seen how to pass a custom neural network in the “model” key of the configuration dictionary. Is it possible to pass custom models for the actor and critic networks?.

---

<div class="post-metadata">

**Author:** ![avnishn](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/avnishn/32/1544_2.png) [@avnishn](https://discuss.ray.io/u/avnishn)\
**Post date:** [March 16, 2022, 1:45am UTC](https://discuss.ray.io/t/what-happens-when-you-pass-a-custom-model-to-an-actor-critic-method/5339/2 "2022-03-16T01:45:42Z")

</div>

Completely! Go ahead and check out our custom model examples:

> <https://github.com/ray-project/ray/blob/master/rllib/examples/custom_model_api.py>

> <https://github.com/ray-project/ray/blob/master/rllib/examples/custom_model_loss_and_metrics.py>