# Training frequency in DQN rllib

**URL:** <https://discuss.ray.io/t/training-frequency-in-dqn-rllib/13694>\
**Category:** Uncategorized\
**Created:** [February 12, 2024, 10:41am UTC](https://discuss.ray.io/t/training-frequency-in-dqn-rllib/13694 "2024-02-12T10:41:44Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![Hami](https://avatars.discourse-cdn.com/v4/letter/h/67e7ee/32.png) [@Hami](https://discuss.ray.io/u/Hami)\
**Post date:** [February 12, 2024, 10:41am UTC](https://discuss.ray.io/t/training-frequency-in-dqn-rllib/13694/1 "2024-02-12T10:41:44Z")

</div>

I want to specify the training frequency based on timesteps for DQN in RLlib but I couldn’t find the corresponding parameters. I run my code for some iterations (using `algorithm.train()`) and in each iterations I have 1000 timesteps (`episode_size=1000`, so one episode in each iteration), the `train_batch_size=32`, but I don’t know how many times (every how many timesteps) the network is updated in each iteration. I am confused with these parameters, any helps?