# Police-based algorithm

**URL:** <https://community.konduit.ai/t/police-based-algorithm/66>\
**Category:** RL4J\
**Created:** [January 11, 2020, 8:11am UTC](https://community.konduit.ai/t/police-based-algorithm/66 "2020-01-11T08:11:38Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![benjamin](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/benjamin/32/26_2.png) [@benjamin](https://community.konduit.ai/u/benjamin)\
**Post date:** [January 11, 2020, 8:11am UTC](https://community.konduit.ai/t/police-based-algorithm/66/1 "2020-01-11T08:11:38Z")

</div>

About RL4j. To my knowledge, RL4j now support value-based rl algorithms like DQN(Double-DQN), any plan to develop policy-based algorithm ?

---

<div class="post-metadata">

**Author:** ![saudet](https://yyz1.discourse-cdn.com/flex035/user_avatar/community.konduit.ai/saudet/32/69_2.png) [@saudet](https://community.konduit.ai/u/saudet)\
**Post date:** [January 20, 2020, 2:13am UTC](https://community.konduit.ai/t/police-based-algorithm/66/2 "2020-01-20T02:13:39Z")

</div>

It already does A3C, for example, check this example: [https://github.com/eclipse/deeplearning4j-examples/blob/master/rl4j-examples/src/main/java/org/deeplearning4j/examples/rl4j/A3CALE.java](https://github.com/eclipse/deeplearning4j-examples/blob/master/rl4j-examples/src/main/java/org/deeplearning4j/examples/rl4j/A3CALE.java)