在概率论和机器学习中，多臂赌博机问题（）有时称为K-或N-臂赌博机问题（）'，是一个必须在竞争（替代）之间分配一组固定的有限资源的问题。当每个选择的属性在分配时仅部分已知时，以最大化其预期收益的方式进行选择，并且随着时间的推移或通过向该选择分配资源可能会更好地被理解。这是一个经典的强化学习问题，体现了探索-利用权衡困境'，并且是否继续使用当前机器或尝试不同的机器。多臂赌博机问题也属于随机调度的广义范畴。
在该问题中，每台机器根据该机器特定的概率分布提供随机奖励，该奖励是先验未知的。赌徒的目标是最大化通过一系列杠杆拉动所获得的奖励总和。约翰·C·吉廷斯首次发表的吉廷斯指数定理给出了最大化预期折扣奖励的最优策略。
参考资料
延伸阅读
*
*.
*.
*.
*.
*.
- .
*
*
外部链接
*[https://github.com/fmr-llc/mabwiser MABWiser], open source Python implementation of bandit strategies that supports context-free, parametric and non-parametric contextual policies with built-in parallelization and simulation capability.
*[https://mloss.org/software/view/415/ PyMaBandits] , open source implementation of bandit strategies in Python and Matlab.
*[https://github.com/Nth-iteration-labs/contextual Contextual] , open source R package facilitating the simulation and evaluation of both context-free and contextual Multi-Armed Bandit policies.
*[http://bandit.sourceforge.net bandit.sourceforge.net Bandit project] , open source implementation of bandit strategies.
*[https://github.com/jkomiyama/banditlib Banditlib] , Open-Source implementation of bandit strategies in C++.
*[https://archive.today/20121212095047/http://www.cs.washington.edu/research/jair/volume4/kaelbling96a-html/node6.html Leslie Pack Kaelbling and Michael L. Littman (1996). Exploitation versus Exploration: The Single-State Case].
- Tutorial: Introduction to Bandits: Algorithms and Theory. [http://techtalks.tv/talks/54451/ Part1] . [http://techtalks.tv/talks/54455/ Part2] .
- [https://feynmanlectures.caltech.edu/info/exercises/Feynmans_restaurant_problem.html Feynman's restaurant problem], a classic example (with known answer) of the exploitation vs. exploration tradeoff.
- [http://www.chrisstucchio.com/blog/2012/bandit_algorithms_vs_ab.html Bandit algorithms vs. A-B testing] .
- [http://homes.di.unimi.it/~cesabian/Pubblicazioni/banditSurvey.pdf S. Bubeck and N. Cesa-Bianchi A Survey on Bandits] .
- [https://arxiv.org/abs/1508.03326 A Survey on Contextual Multi-armed Bandits] , a survey/tutorial for Contextual Bandits.
- [https://mpatacchiola.github.io/blog/2017/08/14/dissecting-reinforcement-learning-6.html Blog post on multi-armed bandit strategies, with Python code] .
*[https://pavlov.tech/2019/03/02/animated-multi-armed-bandit-policies/ Animated, interactive plots] illustrating Epsilon-greedy, , and Upper Confidence Bound exploration/exploitation balancing strategies.
评论 (0)