Eclectic-Sheep / sheeprl

Distributed Reinforcement Learning accelerated by Lightning Fabric
https://eclecticsheep.ai
Apache License 2.0
303 stars 31 forks source link

Let Dreamers share data for distributed training #213

Open belerico opened 7 months ago

belerico commented 7 months ago

As we do in the coupled version of SAC, where we gather data from all ranks before running a distributed update, we should add the possibility for all Dreamer's implementaation (P2E included) to gather data from all ranks before running a distributed update. We could also let the user choose the preferred behavior.

cc @michele-milesi