# \[Impala\] I'm getting a zero vf\_loss, policy\_loss after only 16k steps

**URL:** <https://discuss.ray.io/t/impala-im-getting-a-zero-vf-loss-policy-loss-after-only-16k-steps/2036>\
**Category:** RLlib\
**Created:** [May 4, 2021, 2:13pm UTC](https://discuss.ray.io/t/impala-im-getting-a-zero-vf-loss-policy-loss-after-only-16k-steps/2036 "2021-05-04T14:13:25Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Clement\_Collgon](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/clement_collgon/32/353_2.png) [@Clement\_Collgon](https://discuss.ray.io/u/Clement_Collgon)\
**Post date:** [May 4, 2021, 2:13pm UTC](https://discuss.ray.io/t/impala-im-getting-a-zero-vf-loss-policy-loss-after-only-16k-steps/2036/1 "2021-05-04T14:13:25Z")

</div>

Hello,

 ![image](https://us1.discourse-cdn.com/flex020/uploads/ray/original/1X/e6b1a3a5c791f245da3bbe16e3e1779f71a8c7ef.png)

Do you have any idea what I might have been doing wrong? Is the policy\_reward\_mean too high and should be in the 0 - 1 range?

Thanks in advance

---

<div class="post-metadata">

**Author:** ![Clement\_Collgon](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/clement_collgon/32/353_2.png) [@Clement\_Collgon](https://discuss.ray.io/u/Clement_Collgon)\
**Post date:** [May 6, 2021, 8:55am UTC](https://discuss.ray.io/t/impala-im-getting-a-zero-vf-loss-policy-loss-after-only-16k-steps/2036/2 "2021-05-06T08:55:12Z")

</div>

Still have no clue with this. Also wondering, what is the best multi-agent algorithm on rllib right now for continuous control ? Seems to be MADDPG however, it is not too stable. MAPPO doesn’t do well and impala is bugged