Giters

fidelity / mabwiser

[IJAIT 2021] MABWiser: Contextual Multi-Armed Bandits Library

Home Page:https://fidelity.github.io/mabwiser/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Parallel fit/predict for contextual policies

risufaj opened this issue · comments

commented

In MAB.py line 876
There is a comment that says to not use parallel fit or predict for contextual policies, but it's not clear why that needs to be the case?

Any help would be appreciated.

commented

Hi @risufaj

Very keen observation. All of the contextual policies have implementations that benefit from multi-core processing. As such we do not also parallelize across arms (for fit) or contexts (for predict) as that could actually slow down performance.