[DO NOT CLOSE] Library TODOs and call for contributions

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

No files, tests, or entry points are named. Choose one unchecked item, follow its linked issue where provided (#76, #117, or #52), and define done as implementing that item and updating this checklist.

Written by the indexing model from the issue text.