Manon Flageat

QD resume function

1

Hi, This pull request proposes a definition of a resume function for QD algorithms, based on previous resume functions from Sferes2. It also provides the corresponding tests. This request also...

Re-write the `insert()` method of `Replay Buffer` to fix #71 and #70. This fix also avoids the error raised in #67. I tested this new buffer on the HalfCheetah with...

Hi :) The current PGAME Replay Buffer is using [jax.lax.dynamic_update_slice](https://jax.readthedocs.io/en/latest/_autosummary/jax.lax.dynamic_update_slice.html) to add new transition to the replay buffer. However, this is not acting like a circular buffer, meaning that if...

PGAME add dead transition to Replay Buffer

2

Hi :) It seems that the current implementation of PGAME is adding to the Replay-Buffer all the transitions that are collected in the environment, meaning also transitions that occur after...

PGAME replay buffer addition fail for large batch-size

2

Hello :) The current implementation of the PGAME emitter is failing for large batch-size (here for example 32768) with the following error: ``` Traceback (most recent call last): File "main.py",...

This PR allows to consider the extra-scores for addition to the container to make the MapElitesRepertoire API more general. **Important note - API modification** The `add()` method of the repertoire...

Add algorithm MAP-Elites-ES to QDax

1

Related to #81 This PR adds MAP-Elites-ES to QDax. The complete MAP-Elites-ES algorithm is implemented as an emitter, including the biased sampling from the repertoire, in `qdax/core/emitters/mees_emitter.py`. `qdax/utils/sampling.py` also provide...