mabwiser

mabwiser copied to clipboard

How to use Categorical variables as context?

1

Hi team, I am working on Contextual MAB, and though the example mentions "subscriber" as 0,1. But I was curious to know if I could use a different categorical variable,...

aveshadt

[WIP] Minimal changes necessary for Spock integration

1

Encompasses the minimal amount of changes needed to integrate Spock. Unit tests adjusted for all changes. 100% pass. The only fundamental change to the API is that TreeBandit parameters are...

ncilfone

Line 242 of mabwiser.linear.py ``` python arm_expectations[nonrandom_indices] = np.array([self.arm_to_model[arm].predict(nonrandom_context) for arm in arms]).T ``` if there is an epsilon > 0, and low numbers of context provided can result in...

tk-MF

Bias in Tie-Breaking for Equivalent Arms in EpsilonGreedy and Linear MABs

1

Hi, thanks for the excellent **mabwiser** package! I’m experimenting with delayed rewards and have noticed that some MAB algorithms show bias when selecting between equivalent arms, i.e., when splitting ties....

emanuele

Indicating available / applicable arms

3

Hello! Thanks for this nice project! I'm currently integrating mabwiser into my project. I have the situation that in given contexts certain arms are not applicable and shouldn't be considered...

leandrolanzieri

Visualise arms for monitoring

3

How can i visualise the arms for each different algorithm to monitor this in production?

theobouwman