Luca Grillotti

Related issues: #181 This PR introduces: A MAP-Annealing repertoire `MAERepertoire` which can be used to run a [CMA MAP-Annealing](https://arxiv.org/pdf/2205.10752) algorithm (CMA-MAE). ## Checks - [ ] a clear description of...

Add MAP-Annealing Repertoire to implement the [Covariance Matrix Adaptation MAP-Annealing](https://arxiv.org/pdf/2205.10752) algorithm (CMA-MAE).

The code of [QDAC](https://github.com/adaptive-intelligent-robotics/QDAC) integrates an implementation of [DOMiNO](https://arxiv.org/abs/2205.13521) compatible with QDax. We should add that implementation to the current codebase of QDax.

As mentioned by @hannah-jan, it’s important to include evaluation metrics of the random initialisation of genotypes so we can see how much the first iterations make a difference.

Add a folder `selectors/`with at least uniform and novelty selectors implemented: - Modify QDPG Emitter, PGA Emitter, MultiEmitter and so on… to use selectors - Add crowding-based selection mechanisms for...

`MAPElitesRepertoire` sampling function should be more modular. For instance, the sampling function can return a pytree of type `MAPElitesRepertoire`, with all the corresponding information (genotypes, fitnesses, descriptors, and so on...)...

Make `MAPElitesRepertoire` more modular so that it can store any kind of information (e.g. observations for AURORA). The idea would be to add some `extra_infos` attribute to it (type: `Dict[str,...

As suggested by @manon-but-yes, it would be great to make QDax types independent from external libraries as much as possible. https://github.com/adaptive-intelligent-robotics/QDax/blob/54fae67977f6cb300cee8d5b18e965573f16b913/qdax/types.py#L20C1-L20C38