Sequential Choice Bandits with Feedback for Personalizing users' experience
Not on the map. Why?
Abstract (arXiv)
In this work, we study sequential choice bandits with feedback. We propose bandit algorithms for a platform that personalizes users' experience to maximize its rewards. For each action directed to a given user, the platform is given a positive reward, which is a non-decreasing function of the action, if this action is below the user's threshold. Users are equipped with a patience budget, and actions that are above the threshold decrease the user's patience. When all patience is lost, the user abandons the platform. The platform attempts to learn the thresholds of the users in order to maximize its rewards, based on two different feedback models describing the information pattern available to the platform at each action. We define a notion of regret by determining the best action to be taken when the platform knows that the user's threshold is in a given interval. We then propose bandit algorithms for the two feedback models and show that upper and lower bounds on the regret are of the order of tildeO(N2/3) and tildeOmega(N2/3), respectively, where N is the total number of users. Finally, we show that the waiting time of any user before receiving a personalized experience is uniform in N.
Key facts. Cited by 2 papers in the map (data through 13 Oct 2026). Builds on 11 of its 25 references that are in the map. First posted on arXiv 5 Jan 2021.
Builds on
11 of 25 references.
References · 11
- 2017Minimax Regret Bounds for Reinforcement Learningcited by 501
- 2018Is Q-learning Provably Efficient?cited by 485
- 2015Cascading Bandits: Learning to Rank in the Cascade Modelcited by 76
- 2018What Doubling Tricks Can and Can't Do for Multi-Armed Banditscited by 69
- 2016On Explore-Then-Commit Strategiescited by 46
- 2018Unifying the stochastic and the adversarial Bandits with Knapsackcited by 12
- 2018Floyd-Warshall Reinforcement Learning: Learning from Past Experiences to Reach New Goalscited by 8
- 2018Online learning with feedback graphs and switching costscited by 8
- 2019Dynamic Learning of Sequential Choice Bandit Problem under Marketing Fatiguecited by 4
- 2020Revenue Maximization and Learning in Products Rankingcited by 4
- 2018Learning with Abandonmentcited by 2
Built on by
Citing papers per year: 2022: 1; 2023: 1.
2 papers.