# Where to start learning model/policy customization?

**URL:** <https://discuss.ray.io/t/where-to-start-learning-model-policy-customization/4090>\
**Category:** RLlib\
**Created:** [November 10, 2021, 3:49pm UTC](https://discuss.ray.io/t/where-to-start-learning-model-policy-customization/4090 "2021-11-10T15:49:01Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Roller44](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/roller44/32/1064_2.png) [@Roller44](https://discuss.ray.io/u/Roller44)\
**Post date:** [November 10, 2021, 3:49pm UTC](https://discuss.ray.io/t/where-to-start-learning-model-policy-customization/4090/1 "2021-11-10T15:49:01Z")

</div>

I am interested in learning how to customize policies/models by reading DQN’s code (because the official RLlib documentation is really hard to follow). However, I feel pretty confused when reading it.

Where I should start to learn/read?  
Is there any clearer tutorial relating to policies/models customization?  
Should I have a strong TensorFlow or PyTorch background?

---

<div class="post-metadata">

**Author:** ![Lars\_Simon\_Zehnder](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/lars_simon_zehnder/32/1185_2.png) [@Lars\_Simon\_Zehnder](https://discuss.ray.io/u/Lars_Simon_Zehnder)\
**Post date:** [November 10, 2021, 3:59pm UTC](https://discuss.ray.io/t/where-to-start-learning-model-policy-customization/4090/2 "2021-11-10T15:59:19Z")

</div>

Probably a good start is the tutorial from @sven1977 : [Anyscale - Hands-on Reinforcement Learning with Ray’s RLlib](https://www.anyscale.com/events/2021/06/24/hands-on-reinforcement-learning-with-rays-rllib)

A next step could be to start with some examples: [ray/rllib/examples at master · ray-project/ray · GitHub](https://github.com/ray-project/ray/tree/master/rllib/examples)