search

LucasAlegre / morl-baselines

Multi-Objective Reinforcement Learning algorithms implementations.
https://lucasalegre.github.io/morl-baselines
MIT License
271 stars 44 forks source link

Offline Training #101

Closed AsadJeewa closed 2 months ago

AsadJeewa commented 3 months ago

Thank you for the repo. Can the algorithms be trained offline?

ffelten commented 3 months ago

Hi,

All algorithms are currently compatible with the MO-Gymnasium API. So although multi policy algorithms are made to be trained offline for various trade-offs, we do not support training on a fixed dataset.