# What's the right way of implementing policy gradient?

**URL:** <https://discuss.pytorch.org/t/whats-the-right-way-of-implementing-policy-gradient/4003>\
**Category:** reinforcement-learning\
**Created:** [June 14, 2017, 4:20am UTC](https://discuss.pytorch.org/t/whats-the-right-way-of-implementing-policy-gradient/4003 "2017-06-14T04:20:37Z")\
**Posts on this page:** 1\
**Page:** 2

<div class="post-metadata">

**Author:** ![vmoens](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/vmoens/32/26121_2.png) [@vmoens](https://discuss.pytorch.org/u/vmoens)\
**Post date:** [November 19, 2022, 6:26pm UTC](https://discuss.pytorch.org/t/whats-the-right-way-of-implementing-policy-gradient/4003/22 "2022-11-19T18:26:19Z")

</div>

I edited my answer above 🙂  
Let me know if that helps!

[Previous page](https://discuss.pytorch.org/t/whats-the-right-way-of-implementing-policy-gradient/4003.md?page=1)