# RuntimeWarning: Mean of empty slice with TensorFlow multi-agent PPO

**URL:** <https://discuss.ray.io/t/runtimewarning-mean-of-empty-slice-with-tensorflow-multi-agent-ppo/2752>\
**Category:** RLlib\
**Created:** [July 2, 2021, 10:30am UTC](https://discuss.ray.io/t/runtimewarning-mean-of-empty-slice-with-tensorflow-multi-agent-ppo/2752 "2021-07-02T10:30:08Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![hridayns](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/hridayns/32/1222_2.png) [@hridayns](https://discuss.ray.io/u/hridayns)\
**Post date:** [July 2, 2021, 10:30am UTC](https://discuss.ray.io/t/runtimewarning-mean-of-empty-slice-with-tensorflow-multi-agent-ppo/2752/1 "2021-07-02T10:30:08Z")

</div>

Hello, I have been struggling with this for days so I would really appreciate if someone could help me figure this out! I am not too familiar with the interface here yet, so I have created a question here: [numpy - RLlib PPO reward flat-lines with RuntimeWarning: Mean of empty slice - Stack Overflow](https://stackoverflow.com/questions/68223500/rllib-ppo-reward-flat-lines-with-runtimewarning-mean-of-empty-slice)

Would appreciate any guidance!