Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Refactor QDax, add Policy Gradient Assisted MAP Elites, add CI and doc #6

Merged
merged 130 commits into from
May 30, 2022
Merged

Refactor QDax, add Policy Gradient Assisted MAP Elites, add CI and doc #6

merged 130 commits into from
May 30, 2022

Conversation

felixchalumeau
Copy link
Collaborator

@felixchalumeau felixchalumeau commented May 12, 2022 •
edited
Loading

This pull request aims at applying all the changes that have been discussed by the Adaptative Intelligent Robotics Lab and the research team of InstaDeep to come up with a research package for Quality Diversity and NeuroEvolution in Jax.

In this pull request:

  • the structure of the package has been modified
  • the algorithm of MAP-Elites is the same but the style has been changed: MAP-Elites is implemented as a class
  • the Policy Gradient Emitter is introduced: using the Policy Gradient Emitter with MAP-Elites enables to run Policy Gradient Map-Elites
  • wrappers have been introduced to get informations necessary to build behavior and state descriptors
  • the pointmaze environment has been added
  • tests have been introduced, to check behavior of the MapElitesRepertoire, as well as a training script of MAP-Elites and PGA MAP-Elites, that checks that the code is running (no performance test)
  • a documentation has been added, using mkdocs and readthedocs
  • pre-commits have been applied and added
  • support for docker and conda envs have been added, while keeping singularity available as well
  • a CI has been introduced, it checks that the docker image can be build, it checks that the doc can be build, it checks that the code respects style rules and finally, it checks that the tests pass.
  • the example notebook of MAP-Elites has been updated
  • an example notebook of PGA MAP Elites has been added
  • README has been updated
  • an MIT License has been added
  • the setup file has been updated

This would be tagged version 0.0.2 of the QDax package.

felixchalumeau and others added 30 commits March 9, 2022 19:09
@felixchalumeau
run pre-commit
4f31e7e
@felixchalumeau
add instadeep version of mapelites + envs
922a8a5
@felixchalumeau
remove mapelites config
4fdf0fc
@felixchalumeau
update style
9c7d9bc
@felixchalumeau
add readme
fe91eea
first round refactor - TO TEST
74bcc1e
first working version after refactoring environment and rollout funct…
4e7dcf7 
…ions, playstep
@felixchalumeau
minor style modifs
a082a77
test refactor - attempt at implementing both options of rollout function
8b40a94
@felixchalumeau
new map elites training script using batched envs
c396f5a
@felixchalumeau
wip: skeleton style guideline
e62e462
@felixchalumeau
merge refactor and resolve conflicts
c800bc6
comparison tests for all the refactor version with the original version
ce7c964
@felixchalumeau
Merge branch 'refactor' into 1-instadeep-mapelites
ae832fd
@felixchalumeau
refactor style
0e170d9
@ranzenTom
WIP
3e49a43
@ranzenTom
Merge branch '1-instadeep-mapelites' into 2-instadeep-new-structure-s…
ea8229f 
…uggestion

# Conflicts:
#	experiments/train_mapelites.py
#	experiments/train_mapelites_v2.py
@ranzenTom
WIP
d6d0f08
@ranzenTom
WIP
e9dd2e4
@ranzenTom
add missing init
abbfaf8
@ranzenTom
added utils
60f69cc
@ranzenTom
WIP
502ddb3
@ranzenTom
WIP
c7c11ed
@ranzenTom
adding missing constants and wrappers
746f054
@ranzenTom
forgot static args
30bba1c
@ranzenTom
forgot static args
0865dc0
@ranzenTom
forgot static args
24a716d
@ranzenTom
forgot static args
85a14a7
@ranzenTom
WIP
c24c851
@ranzenTom
WIP
31dd074
@felixchalumeau felixchalumeau marked this pull request as ready for review May 13, 2022 11:32
@Lookatator Lookatator mentioned this pull request May 20, 2022
Closed
@Lookatator Lookatator linked an issue May 20, 2022 that may be closed by this pull request
IsoDD sigma_line is a vector instead of a scalar #9
Closed
@felixchalumeau felixchalumeau merged commit fe49ef3 into adaptive-intelligent-robotics:main May 30, 2022
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@limbryan limbryan limbryan approved these changes

@Lookatator Lookatator Lookatator approved these changes

@maxiallard maxiallard maxiallard approved these changes

@ranzenTom ranzenTom Awaiting requested review from ranzenTom

Assignees

@felixchalumeau felixchalumeau

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.

IsoDD sigma_line is a vector instead of a scalar
6 participants
@felixchalumeau @maxiallard @Lookatator @limbryan @ranzenTom @remidebette