# Algorithms for slate bandits with non-separable reward functions

arXiv: https://arxiv.org/abs/2004.09957 · HTML: https://mlsanity.com/paper/2004.09957/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Apr 2020.

## Built on by (most cited first, 6 of 6)

- [Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Arms](https://mlsanity.com/paper/2202.13001/) (2022)
- [Global Rewards in Restless Multi-Armed Bandits](https://mlsanity.com/paper/2406.00738/) (2024)
- [Combining Reward and Rank Signals for Slate Recommendation](https://mlsanity.com/paper/2107.12455/) (2021)
- [Efficient Algorithms for Logistic Contextual Slate Bandits with Bandit Feedback](https://mlsanity.com/paper/2506.13163/) (2025)
- [Edge-Compatible Reinforcement Learning for Recommendations](https://mlsanity.com/paper/2112.05812/) (2021)
- [Contextual Slate GLM Bandits with Limited Adaptivity](https://mlsanity.com/paper/2606.31449/) (2026)

## Abstract (arXiv)

In this paper, we study a slate bandit problem where the function that determines the slate-level reward is non-separable: the optimal value of the function cannot be determined by learning the optimal action for each slot. We are mainly concerned with cases where the number of slates is large relative to the time horizon, so that trying each slate as a separate arm in a traditional multi-armed bandit, would not be feasible. Our main contribution is the design of algorithms that still have sub-linear regret with respect to the time horizon, despite the large number of slates. Experimental results on simulated data and real-world data show that our proposed method outperforms popular benchmark bandit algorithms.