Stochastic bandits robust to adversarial corruptions
We introduce a new model of stochastic bandits with adversarial corruptions which aims to
capture settings where most of the input follows a stochastic pattern but some fraction of it …
capture settings where most of the input follows a stochastic pattern but some fraction of it …
[图书][B] Effective online decision-making in complex multi-agent systems
T Lykouris - 2019 - search.proquest.com
The emergence of online marketplaces has introduced important new dimensions to online
decision-making. Classical algorithms developed to guarantee worst-case performance …
decision-making. Classical algorithms developed to guarantee worst-case performance …
Bandits with Temporal Stochastic Constraints
P Agrawal, T Tulabandhula - arXiv preprint arXiv:1811.09026, 2018 - arxiv.org
We study the effect of impairment on stochastic multi-armed bandits and develop new ways
to mitigate it. Impairment effect is the phenomena where an agent only accrues reward for an …
to mitigate it. Impairment effect is the phenomena where an agent only accrues reward for an …