# Cannot reproduce training results in evaluation even on same dataset

**URL:** <https://discuss.ray.io/t/cannot-reproduce-training-results-in-evaluation-even-on-same-dataset/8280>\
**Category:** RLlib\
**Created:** [November 15, 2022, 12:11pm UTC](https://discuss.ray.io/t/cannot-reproduce-training-results-in-evaluation-even-on-same-dataset/8280 "2022-11-15T12:11:29Z")\
**Posts on this page:** 1\
**Showing post:** 2

<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 20, 2022, 12:53pm UTC](https://discuss.ray.io/t/cannot-reproduce-training-results-in-evaluation-even-on-same-dataset/8280/2 "2022-11-20T12:53:50Z")

</div>

@SVH This has been answered by @mannyv in the [reply](https://discuss.ray.io/t/training-mean-reward-vs-evaluation-mean-rewward/8273/2) to a similar problem of yours, I guess.

The `explore` attribute for evaluation has to be set to `True` to achieve comparable results to training.

---

_[View the full topic](https://discuss.ray.io/t/cannot-reproduce-training-results-in-evaluation-even-on-same-dataset/8280)._