mlsanityData to 7 Oct 2026

Latent Bandits Revisited

arXiv 2006.08714 ↗First posted 15 Jun 2020cs.LG cs.AI stat.MLcited by 43

Not on the map. Why?

Abstract (arXiv)

A latent bandit problem is one in which the learning agent knows the arm reward distributions conditioned on an unknown discrete latent state. The primary goal of the agent is to identify the latent state, after which it can act optimally. This setting is a natural midpoint between online and offline learning---complex models can be learned offline with the agent identifying latent state online---of practical relevance in, say, recommender systems. In this work, we propose general algorithms for this setting, based on both upper confidence bounds (UCBs) and Thompson sampling. Our methods are contextual and aware of model uncertainty and misspecification. We provide a unified theoretical analysis of our algorithms, which have lower regret than classic bandit policies when the number of latent states is smaller than actions. A comprehensive empirical study showcases the advantages of our approach.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 5; 2023: 10; 2024: 8; 2025: 6; 2026: 2.

43 papers.

Sort:

By area:

  1. 2021Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learningcited by 65
  2. 2021Meta-Thompson Samplingcited by 62
  3. 2021Hierarchical Bayesian Banditscited by 33
  4. 2021No Regrets for Learning the Prior in Banditscited by 29
  5. 2021Metadata-based Multi-Task Bandits with Bayesian Hierarchical Modelscited by 24
  6. 2022Deep Hierarchy in Banditscited by 18
  7. 2021Thompson Sampling with a Mixture Priorcited by 15
  8. 2022Learning Mixtures of Linear Dynamical Systemscited by 15
  9. 2022Mixed-Effect Thompson Samplingcited by 14
  10. 2021Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Banditscited by 13
  11. 2023Scalable Neural Contextual Bandit for Recommender Systemscited by 12
  12. 2023Optimal Algorithms for Latent Bandits with Cluster Structurecited by 11
31 more
  1. 2021Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Banditscited by 10
  2. 2024Pretraining Decision Transformers with Reward Prediction for In-Context Multi-task Structured Bandit Learningcited by 10
  3. 2021Interaction-Grounded Learningcited by 9
  4. 2022Non-stationary Bandits and Meta-Learning with a Small Set of Optimal Armscited by 8
  5. 2021Combining Online Learning and Offline Learning for Contextual Bandits with Deficient Supportcited by 7
  6. 2023Thompson Sampling with Diffusion Generative Priorcited by 7
  7. 2024Meta Clustering of Neural Banditscited by 7
  8. 2021Thompson Sampling for Bandits with Clustered Armscited by 6
  9. 2021Feature and Parameter Selection in Stochastic Linear Banditscited by 5
  10. 2023Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learningcited by 5
  11. 2024Diffusion Models Meet Contextual Banditscited by 5
  12. 2024Partially Observable Contextual Bandits with Linear Payoffscited by 5
  13. 2023Online learning in bandits with predicted contextcited by 4
  14. 2024Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Banditscited by 4
  15. 2025Transfer Learning in Latent Contextual Bandits with Covariate Shift Through Causal Transportabilitycited by 4
  16. 2023Context-lumpable stochastic banditscited by 3
  17. 2022Information-Gathering in Latent Banditscited by 2
  18. 2024Efficient Learning of POMDPs with Known Observation Model in Average-Reward Settingcited by 1
  19. 2024Competing Bandits in Decentralized Contextual Matching Marketscited by 1
  20. 2025A Classification View on Meta Learning Banditscited by 1
  21. 2025Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticitycited by 1
  22. 2023Adversarial Online Collaborative Filteringcited by 0
  23. 2023Stochastic Contextual Bandits with Graph-based Contextscited by 0
  24. 2023High Accuracy and Low Regret for User-Cold-Start Using Latent Banditscited by 0
  25. 2023Finite-Time Logarithmic Bayes Regret Upper Boundscited by 0
  26. 2024Identifiable Latent Bandits: Leveraging observational data for personalized decision-makingcited by 0
  27. 2025Leveraging priors on distribution functions for multi-arm banditscited by 0
  28. 2025Representative Action Selection for Large Action Space Bandit Familiescited by 0
  29. 2025Latent Preference Banditscited by 0
  30. 2026Latent Order Banditscited by 0
  31. 2026CUPID in the Model Zoo: Online Matchmaking for Selecting Your Dream LLMcited by 0