# \[rllib\] different networks for different policies

**URL:** <https://discuss.ray.io/t/rllib-different-networks-for-different-policies/1093>\
**Category:** RLlib\
**Created:** [March 3, 2021, 9:44am UTC](https://discuss.ray.io/t/rllib-different-networks-for-different-policies/1093 "2021-03-03T09:44:10Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Jogima-cyber](https://sea2.discourse-cdn.com/flex020/user_avatar/discuss.ray.io/jogima-cyber/32/454_2.png) [@Jogima-cyber](https://discuss.ray.io/u/Jogima-cyber)\
**Post date:** [March 3, 2021, 9:44am UTC](https://discuss.ray.io/t/rllib-different-networks-for-different-policies/1093/1 "2021-03-03T09:44:10Z")

</div>

Hello there !  
I know how to plug a custom net for a policy like this :  
“model”: {  
“custom\_model”: “torch\_net”  
}  
But I don’t know how to specify different networks for different policies when there are more than one policy and only one training method (A2C for example). I didn’t find anything in the doc, and I didn’t find anything in the examples on github.  
Thanks for your help !

---

<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:** [March 3, 2021, 9:51am UTC](https://discuss.ray.io/t/rllib-different-networks-for-different-policies/1093/2 "2021-03-03T09:51:41Z")

</div>

Hey @Jogima-cyber  
you can specify per-policy config overrides via your multi-agent setup. Like so:

```auto

# You multi-agent policy dict:
policies = {
    "pol1": ([class], [obs-space], [action-space], {"model": {"fcnet_hiddens": [50, 50]}}), # <- will use default fc net
    "pol2": ([class], [obs-space], [action-space], {"model": {"custom_model": "torch_net"}}), # <- will use your custom torch model
}

```

Then your config:

```auto
config:
    multiagent: 
        policies: policies # <- dict from above

```