# MNL-Bandit: A Dynamic Learning Approach to Assortment Selection

arXiv: https://arxiv.org/abs/1706.03880 · HTML: https://mlsanity.com/paper/1706.03880/

## Key facts

- Cited by 50 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2017.

## Built on by (most cited first, 30 of 50)

- [Online Learning via Offline Greedy Algorithms: Applications in Market Design and Optimization](https://mlsanity.com/paper/2102.11050/) (2021)
- [Designing Decision Support Systems Using Counterfactual Prediction Sets](https://mlsanity.com/paper/2306.03928/) (2023)
- [Transfer Learning for Contextual Multi-armed Bandits](https://mlsanity.com/paper/2211.12612/) (2022)
- [Multinomial Logit Contextual Bandits: Provable Optimality and Practicality](https://mlsanity.com/paper/2103.13929/) (2021)
- [Dynamic pricing and assortment under a contextual MNL demand](https://mlsanity.com/paper/2110.10018/) (2021)
- [Nearly Minimax Optimal Regret for Multinomial Logistic Bandit](https://mlsanity.com/paper/2405.09831/) (2024)
- [Improved Online Confidence Bounds for Multinomial Logistic Bandits](https://mlsanity.com/paper/2502.10020/) (2025)
- [Adversarial Combinatorial Bandits with General Non-linear Reward Functions](https://mlsanity.com/paper/2101.01301/) (2021)
- [UCB-based Algorithms for Multinomial Logistic Regression Bandits](https://mlsanity.com/paper/2103.11489/) (2021)
- [Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework](https://mlsanity.com/paper/2202.13227/) (2022)
- [From Finite to Countable-Armed Bandits](https://mlsanity.com/paper/2105.10721/) (2021)
- [Doubly High-Dimensional Contextual Bandits: An Interpretable Model for Joint Assortment-Pricing](https://mlsanity.com/paper/2309.08634/) (2023)
- [Diffusion Approximations for a Class of Sequential Testing Problems](https://mlsanity.com/paper/2102.07030/) (2021)
- [Contextual Online Uncertainty-Aware Preference Learning for Human Feedback](https://mlsanity.com/paper/2504.19342/) (2025)
- [Towards Human-AI Complementarity in Matching Tasks](https://mlsanity.com/paper/2508.13285/) (2025)
- [Offline Learning for Combinatorial Multi-armed Bandits](https://mlsanity.com/paper/2501.19300/) (2025)
- [Contextual Multinomial Logit Bandits with General Value Functions](https://mlsanity.com/paper/2402.08126/) (2024)
- [Stop Relying on No-Choice and Do not Repeat the Moves: Optimal, Efficient and Practical Algorithms for Assortment Optimization](https://mlsanity.com/paper/2402.18917/) (2024)
- [Learning an Optimal Assortment Policy under Observational Data](https://mlsanity.com/paper/2502.06777/) (2025)
- [Multiplier Bootstrap-based Exploration](https://mlsanity.com/paper/2302.01543/) (2023)
- [Interpolating Item and User Fairness in Multi-Sided Recommendations](https://mlsanity.com/paper/2306.10050/) (2023)
- [Think Before You Duel: Understanding Complexities of Preference Learning under Constrained Resources](https://mlsanity.com/paper/2312.17229/) (2023)
- [Enhancing Preference-based Linear Bandits via Human Response Time](https://mlsanity.com/paper/2409.05798/) (2024)
- [Enjoying Non-linearity in Multinomial Logistic Bandits: A Minimax-Optimal Algorithm](https://mlsanity.com/paper/2507.05306/) (2025)
- [MNL-Bandit with Knapsacks: a near-optimal algorithm](https://mlsanity.com/paper/2106.01135/) (2021)
- [Active Learning for Non-Parametric Choice Models](https://mlsanity.com/paper/2208.03346/) (2022)
- [Low-Rank Online Dynamic Assortment with Dual Contextual Information](https://mlsanity.com/paper/2404.17592/) (2024)
- [Dynamic Assortment Selection and Pricing with Censored Preference Feedback](https://mlsanity.com/paper/2504.02324/) (2025)
- [Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options](https://mlsanity.com/paper/2510.18713/) (2025)
- [Algorithm for Contextual Queueing Bandits with Rate-Optimal Queue Length Regret](https://mlsanity.com/paper/2606.09668/) (2026)

## Abstract (arXiv)

We consider a dynamic assortment selection problem, where in every round the retailer offers a subset (assortment) of N substitutable products to a consumer, who selects one of these products according to a multinomial logit (MNL) choice model. The retailer observes this choice and the objective is to dynamically learn the model parameters, while optimizing cumulative revenues over a selling horizon of length T. We refer to this exploration-exploitation formulation as the MNL-Bandit problem. Existing methods for this problem follow an "explore-then-exploit" approach, which estimate parameters to a desired accuracy and then, treating these estimates as if they are the correct parameter values, offers the optimal assortment based on these estimates. These approaches require certain a priori knowledge of "separability", determined by the true parameters of the underlying MNL model, and this in turn is critical in determining the length of the exploration period. (Separability refers to the distinguishability of the true optimal assortment from the other sub-optimal alternatives.) In this paper, we give an efficient algorithm that simultaneously explores and exploits, achieving performance independent of the underlying parameters. The algorithm can be implemented in a fully online manner, without knowledge of the horizon length T. Furthermore, the algorithm is adaptive in the sense that its performance is near-optimal in both the "well separated" case, as well as the general parameter setting where this separation need not hold.