MABWiser: A Parallelizable Contextual Multi-Armed Bandit Library for Python
Contextual multi-armed bandit algorithms serve as an effective technique to address online sequential decision-making problems. Despite their popularity, when it comes to off-the-shelf tools the library support remains limited, in particular for the Python technology stack. To fill this gap, in this paper we present a system that provides context-free, parametric and nonparametric contextual multi-armed bandit models. The available bandit policies accommodate both batch and online learning. The MABWISER system is implemented as an open-source Python library. Our design enables built-in parallelization to speed up training and test components for scalability while ensuring the reproducibility of results. We present a running example to highlight the user-friendly nature of the public interface and discuss the simulation capability of the library for hyperparameter tuning and rapid experimentation.
Code (1)
Tasks
Decision MakingSequential Decision MakingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
OSOM: A simultaneously optimal algorithm for multi-armed and linear contextual bandits
We consider the stochastic linear (multi-armed) contextual bandit problem with the possibility of hidden simple multi-armed bandit structure in which the rewards are independent of the contextual information. Algorithms …
Multi-Armed BanditsDeep Contextual Multi-armed Bandits
Contextual multi-armed bandit problems arise frequently in important industrial applications. Existing solutions model the context either linearly, which enables uncertainty driven (principled) exploration, or non-linear…
MarketingMulti-Armed BanditsThompson SamplingOnline learning with Corrupted context: Corrupted Contextual Bandits
We consider a novel variant of the contextual bandit problem (i.e., the multi-armed bandit with side-information, or context, available to a decision-maker) where the context used at each decision may be corrupted ("usel…
Multi-Armed BanditsA Survey on Contextual Multi-armed Bandits
In this survey we cover a few stochastic and adversarial contextual bandit algorithms. We analyze each algorithm's assumption and regret bound.
Multi-Armed BanditsSurveyAnalysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits
Contextual multi-armed bandits are classical models in reinforcement learning for sequential decision-making associated with individual information. A widely-used policy for bandits is Thompson Sampling, where samples fr…
Decision MakingMulti-Armed Banditsreinforcement-learningReinforcement Learning (RL)+2