# Disallowing actions for an agent in multi agent setting
**URL:** https://discuss.ray.io/t/disallowing-actions-for-an-agent-in-multi-agent-setting/2461
**Category:** RLlib
**Created:** [June 9, 2021, 9:43am UTC](https://discuss.ray.io/t/disallowing-actions-for-an-agent-in-multi-agent-setting/2461 "2021-06-09T09:43:05Z")
**Posts on this page:** 3
**Page:** 1
### Author:  [@Saurabh\_Arora](https://discuss.ray.io/u/Saurabh_Arora)
#### Post date: [June 9, 2021, 9:43am UTC](https://discuss.ray.io/t/disallowing-actions-for-an-agent-in-multi-agent-setting/2461/1 "2021-06-09T09:43:05Z")
Hi everyone.
I am trying to setup a two agent setup with some special requirements. I expect agent1 to use only subset1 of action-set and agent2 to use only subset2 of same action-set. subset1 and subset2 may or may not overlap. Can anyone please help me know where to start and what to read for setting this up?
---
### Author:  [@sven1977](https://discuss.ray.io/u/sven1977)
#### Post date: [June 11, 2021, 9:32am UTC](https://discuss.ray.io/t/disallowing-actions-for-an-agent-in-multi-agent-setting/2461/2 "2021-06-11T09:32:44Z")
Hey @Saurabh_Arora , you can tell your “multiagent” setup to use different action spaces for the two policies:
```auto
config:
multiagent:
policies:
pol1: (None, [obs-space], [action-space pol1], {})
pol2: (None, [obs-space], [action-space pol2], {})
```
Does this make sense?
---
### Author:  [@Saurabh\_Arora](https://discuss.ray.io/u/Saurabh_Arora)
#### Post date: [June 15, 2021, 11:49am UTC](https://discuss.ray.io/t/disallowing-actions-for-an-agent-in-multi-agent-setting/2461/3 "2021-06-15T11:49:50Z")
I can definitely try that out. For now, this stage of code went on hold.