Deciding when to quit the gambler's ruin game with unknown probabilities
In the standard definition of the classical gambler's ruin game, a persistent player enters in a
stochastic process with an initial budget b 0, which is, round after round, either increased by …
stochastic process with an initial budget b 0, which is, round after round, either increased by …
Controlling Tail Risk in Online Ski-Rental
The classical ski-rental problem admits a textbook 2-competitive deterministic algorithm, and
a simple randomized algorithm that is e/e-1-competitive in expectation. The randomized …
a simple randomized algorithm that is e/e-1-competitive in expectation. The randomized …
The Survival Bandit Problem
We study the survival bandit problem, a variant of the multi-armed bandit problem with a
constraint on the cumulative reward; at each time step, the agent receives a reward in [-1, 1] …
constraint on the cumulative reward; at each time step, the agent receives a reward in [-1, 1] …
Gambler bandits and the regret of being ruined
In this paper we consider a particular class of problems called multiarmed gambler bandits
(MAGB) which constitutes a modified version of the Bernoulli MAB problem where two new …
(MAGB) which constitutes a modified version of the Bernoulli MAB problem where two new …
Simple Modification of the Upper Confidence Bound Algorithm by Generalized Weighted Averages
N Manome, S Shinohara, U Chung - arXiv preprint arXiv:2308.14350, 2023 - arxiv.org
The multi-armed bandit (MAB) problem is a classical problem that models sequential
decision-making under uncertainty in reinforcement learning. In this study, we propose a …
decision-making under uncertainty in reinforcement learning. In this study, we propose a …
Approaching Single-Episode Survival Reinforcement Learning with Safety-Threshold Q-Learning
FS Perotto, M Nargeot, A Ouahbi - International Conference on …, 2024 - Springer
Abstract Survival Reinforcement Learning is a specific type of RL problem constrained by a
risk of ruin. The underlying stochastic sequential decision process with which the agent …
risk of ruin. The underlying stochastic sequential decision process with which the agent …
Optimizing recommendations under abandonment risks: Models and algorithms
User abandonment behaviors are quite common in recommendation applications such as
online shopping recommendation and news recommendation. To maximize its total “reward” …
online shopping recommendation and news recommendation. To maximize its total “reward” …
Survival Multiarmed Bandits with Bootstrapping Methods
P Veroutis, F Godin - arXiv preprint arXiv:2410.16486, 2024 - arxiv.org
The Multiarmed Bandits (MAB) problem has been extensively studied and has seen many
practical applications in a variety of fields. The Survival Multiarmed Bandits (S-MAB) open …
practical applications in a variety of fields. The Survival Multiarmed Bandits (S-MAB) open …
Time is Budget: A Heuristic for Reducing the Risk of Ruin in Multi-armed Gambler Bandits
In this paper we consider Multi-Armed Gambler Bandits (MAGB), a stochastic random
process in which an agent performs successive actions and either loses 1 unit from its …
process in which an agent performs successive actions and either loses 1 unit from its …
[PDF][PDF] HAL Id: hal-03120813 https://hal. archives-ouvertes. fr/hal-03120813
In this paper we consider a particular class of problems called multiarmed gambler bandits
(MAGB) which constitutes a modified version of the Bernoulli MAB problem where two new …
(MAGB) which constitutes a modified version of the Bernoulli MAB problem where two new …