[DO NOT CLOSE] Library TODOs and call for contributions

[matteobettini]

Hello people!

In this issue I will list the things I would really like to have in BenchMARL and will tick them off as they are implemented!

It is also a really good place to find something you would like to contribute.

Features

• [x] Parameter sharing between actors and critics (#95)
• [ ] support for variable number of agents (dead agents)
• [ ] support for turn-based environments (#76)
• [x] Parallel collection and evaluation for non-vectorized environments (#143)(#152)
• [x] Improve checkpointing (just keep last checkpoints) (#102)
• [x] Prioritized replay buffers (#160)
• [x] Use different models and algorithms for different groups (#159 )

Models

• [x] GRU model (#116)
• [X] LSTM model (#103)(#120)
• [x] DeepSets model (#96)
• [ ] Multi-Agent Transformer (#117)

Algorithms

• [ ] MPO and V-MPO
• [ ] HARL algorithms (#52)

Environments

• [ ] Unity ML-Agents
• [x] MAgent2 (#137 )
• [ ] Overcooked
• [ ] Habitat
• [ ] MAMujoco