facebookresearch / facebookresearch/BenchMARL

Adding Level Based Foraging to BenchMARL.

Open
#205 4 comments 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
661
Forks
135
PR merge metrics
No merged PRs in 30d

Description

Hello,

Firstly, BenchMARL has been very helpful for me. I sincerely thank everyone involved for their efforts.

Can we look to add Level Based Foraging ([LBF](https://github.com/semitable/lb-foraging)) to BenchMARL? I have been using LBF for a while, and it is very well supported by [epymarl.](https://github.com/uoe-agents/epymarl) Benchmarking has also been done on LBF in this [paper.](https://arxiv.org/pdf/2006.07869)

Please let me know if this could be helpful.

Contributor guide

Open the contributing guide

Research direction

Start by reviewing BenchMARL's existing task integrations and the linked Level Based Foraging project, then compare how epymarl supports LBF. Determine the integration points needed to make LBF available for BenchMARL benchmarking; done means the environment can be selected and benchmarked consistently within BenchMARL.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.