instadeepai / Mava

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX

Home Page:https://id-mava.readthedocs.io

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Create an update_network function to reduce code duplication

sash-a opened this issue · comments

Feature

Because of the fact that we have a separate actor and critic, we need to update both networks separately, this is leading to a lot of code duplication, for example here.

We should make a function: update_network and then call this twice to update the network to reduce the code duplication.