fix: shared weights with agent type

[AsadJeewa]

What?

Updated agent network types to only share weights between agent types
#427

Why?

When setting shared_weights to true, a single network is created for all agents. It should not be possible to share weights across agent types

How?

changed self._agent_net_keys in systems.py to assign the correct keys (for MADQN, MAPPO, MADDPG)

Extra

If we are happy with this change, would we then need to benchmark?

[arnupretorius]

Thanks @AsadJeewa! 😄

Just see my few comments. Also, did we test this? At the very least we should do some runs on environments with and without different agent types.

[AsadJeewa]

I tested that everything works in multiple different environments with different (openspiel Tic Tac Toe, Petting Zoo Pong) or single-agent types (debugging, Petting Zoo Multiwalker, Flatland) to make sure that the networks were being assigned correctly and that execution proceeds. Since shared_weights default value is True, I think that we should run a small set of benchmarks @RuanJohn

[mmorris44]

• 1 potential issue in 3 places
• 1 debug print statement
• 1 minor comment

[AsadJeewa]

This line (https://github.com/instadeepai/Mava/blob/develop/mava/specs.py#L68) assumes that all environments will follow the naming convention of type_identifier but this is not always the case e.g. OpenSpiel TicTacToe: agents are named player_0 and player_1 so Mava assumes they are the same type. I have created a separate issue for this (#434)

[mmorris44]

PR looks good to go from my side.
Thanks @AsadJeewa!

[arnupretorius]

Thanks @AsadJeewa! 👍