# \[RLlib\] Why some algorithms do not suppport multiagent or discrete/continuous action space?

**URL:** <https://discuss.ray.io/t/rllib-why-some-algorithms-do-not-suppport-multiagent-or-discrete-continuous-action-space/444>\
**Category:** RLlib\
**Created:** [January 14, 2021, 8:08pm UTC](https://discuss.ray.io/t/rllib-why-some-algorithms-do-not-suppport-multiagent-or-discrete-continuous-action-space/444 "2021-01-14T20:08:45Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![51616](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/51616/32/247_2.png) [@51616](https://discuss.ray.io/u/51616)\
**Post date:** [January 14, 2021, 8:08pm UTC](https://discuss.ray.io/t/rllib-why-some-algorithms-do-not-suppport-multiagent-or-discrete-continuous-action-space/444/1 "2021-01-14T20:08:45Z")

</div>

What can I do about algorithms that do not support either action space or multiagent?  
For example, if I want to use MAML in discrete multiagent environment or DQN agent with RNN, can I modify the MAML/DQN agent to support this? Maybe I could contribute some code to support some of the usecase I’m using. Thanks.

---

<div class="post-metadata">

**Author:** ![sven1977](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/sven1977/32/53_2.png) [@sven1977](https://discuss.ray.io/u/sven1977)\
**Post date:** [January 25, 2021, 11:29am UTC](https://discuss.ray.io/t/rllib-why-some-algorithms-do-not-suppport-multiagent-or-discrete-continuous-action-space/444/2 "2021-01-25T11:29:24Z")

</div>

Thanks for reporting this @51616 .

MAML should support discrete actions (in pytorch). There is now a test case with CartPole that proves that.  
Please simply try multi-agent with MAML and report back here.  
The reason it’s not mentioned in the documentation is simply that we haven’t tested this yet.

DQN + RNNs: Not supported for now, but we are planning on adding R2D2-style (off-policy + RNNs) algos this quarter.