mlsanityData to 14 Oct 2026

Distributional Off-Policy Evaluation for Slate Recommendations

arXiv 2308.14165 ↗First posted 27 Aug 2023cs.IR cs.AI cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

Recommendation strategies are typically evaluated by using previously logged data, employing off-policy evaluation methods to estimate their expected performance. However, for strategies that present users with slates of multiple items, the resulting combinatorial action space renders many of these methods impractical. Prior work has developed estimators that leverage the structure in slates to estimate the expected off-policy performance, but the estimation of the entire performance distribution remains elusive. Estimating the complete distribution allows for a more comprehensive evaluation of recommendation strategies, particularly along the axes of risk and fairness that employ metrics computable from the distribution. In this paper, we propose an estimator for the complete off-policy performance distribution for slates and establish conditions under which the estimator is unbiased and consistent. This builds upon prior work on off-policy evaluation for slates and off-policy distribution estimation in reinforcement learning. We validate the efficacy of our method empirically on synthetic data as well as on a slate recommendation simulator constructed from real-world data (MovieLens-20M). Our results show a significant reduction in estimation variance and improved sample efficiency over prior work across a range of slate structures.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 18 of its 49 references that are in the map. First posted on arXiv 27 Aug 2023.

Builds on

18 of 49 references.

References · 18

  1. 2015Doubly Robust Policy Evaluation and Optimizationcited by 158
  2. 2016Optimal and Adaptive Off-policy Evaluation in Contextual Banditscited by 111
  3. 2016Off-policy evaluation for slate recommendationcited by 103
  4. 2019Embarrassingly Shallow Autoencoders for Sparse Datacited by 94
  5. 2020Open Bandit Dataset and Pipeline: Towards Realistic and Reproducible Off-Policy Evaluationcited by 77
  6. 2019Learning Action Representations for Reinforcement Learningcited by 75
  7. 2019Being Optimistic to Be Conservative: Quickly Learning a CVaR Policycited by 63
  8. 2021Universal Off-Policy Evaluationcited by 43
  9. 2014Efficient Learning in Large-Scale Combinatorial Semi-Banditscited by 36
  10. 2020Counterfactual Evaluation of Slate Recommendations with Sequential Reward Interactionscited by 35
  11. 2018Offline Evaluation of Ranking Policies with Click Modelscited by 32
  12. 2022Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Modelcited by 30
6 more
  1. 2021Off-Policy Risk Assessment in Contextual Banditscited by 29
  2. 2019Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learningcited by 28
  3. 2018Best Arm Identification for Contaminated Banditscited by 24
  4. 2015Deep Reinforcement Learning with Attention for Slate Markov Decision Processes with High-Dimensional States and Actionscited by 13
  5. 2021Control Variates for Slate Off-Policy Evaluationcited by 13
  6. 2020Learning Representations of Hierarchical Slates in Collaborative Filteringcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 1.

2 papers.

  1. 2025Time-Constrained Recommendations: Reinforcement Learning Strategies for E-Commercecited by 3
  2. 2026Offline Contextual Bandits in the Presence of New Actionscited by 0