# Meaning of episode\_reward\_mean

**URL:** <https://discuss.ray.io/t/meaning-of-episode-reward-mean/3839>\
**Category:** RLlib\
**Created:** [October 18, 2021, 10:17am UTC](https://discuss.ray.io/t/meaning-of-episode-reward-mean/3839 "2021-10-18T10:17:51Z")\
**Posts on this page:** 1\
**Showing post:** 8

<div class="post-metadata">

**Author:** ![mannyv](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/mannyv/32/606_2.png) [@mannyv](https://discuss.ray.io/u/mannyv)\
**Post date:** [January 10, 2023, 12:09am UTC](https://discuss.ray.io/t/meaning-of-episode-reward-mean/3839/8 "2023-01-10T00:09:10Z")

</div>

Hi @JeanT,

The episode reward is the sum of all the rewards for each timestep in an episode. Yes, you could think of it as discount=1.0.

The mean is taken over the number of episodes not timesteps. The number of episodes is the number of new episodes sampled during the rollout phase or evaluation if it is an evaluation metric.

---

_[View the full topic](https://discuss.ray.io/t/meaning-of-episode-reward-mean/3839)._