instadeepai / Mava

🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX
Apache License 2.0
709 stars 83 forks source link

Enhancement: Make a `network.py` file #972

Closed OmaymaMahjoub closed 8 months ago

OmaymaMahjoub commented 9 months ago

What?

Make a shared file for the networks.

Why?

To avoid redundancy across the single files systems, we made a shared file containing the networks. This approach ensures clarity and is easy to maintain.

How?

Develop the get_networks function to enable user selection between feedforward or recurrent networks, and to specify whether the training is centralized or independent.