Giters

facebookresearch / Pearl

A Production-ready Reinforcement Learning AI Agent Library brought by the Applied Reinforcement Learning team at Meta.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Multi-agent Reinforcement Learning?

paapu88 opened this issue · comments

commented

Dear Developers,
Is multi-agent Reinforcement Learning possible with Pearl
or should one go for https://marllib.readthedocs.io/en/latest/ ?
Terveisin, Markus

commented

Sorry, Pearl was not designed with multi-agent RL in mind. It might be possible to do it with some redesign (or implementing a PearlAgent that plays the role of multiple agents), but this would not be trivial or immediate.