mlsanityData to 7 Oct 2026

Ensemble Sampling

arXiv 1705.07347 ↗First posted 20 May 2017stat.ML cs.AI cs.LGcited by 62

Not on the map. Why?

Abstract (arXiv)

Thompson sampling has emerged as an effective heuristic for a broad range of online decision problems. In its basic form, the algorithm requires computing and sampling from a posterior distribution over models, which is tractable only for simple special cases. This paper develops ensemble sampling, which aims to approximate Thompson sampling while maintaining tractability even in the face of complex models such as neural networks. Ensemble sampling dramatically expands on the range of applications for which Thompson sampling is viable. We establish a theoretical basis that supports the approach and present computational results that offer further insight.

Key facts. Cited by 62 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 May 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 12; 2022: 11; 2023: 14; 2024: 8; 2025: 10; 2026: 6.

62 papers.

Sort:

By area:

  1. 2023Supervised Pretraining Can Learn In-Context Reinforcement Learningcited by 137
  2. 2021Epistemic Neural Networkscited by 120
  3. 2024Self-Exploring Language Models: Active Preference Elicitation for Online Alignmentcited by 63
  4. 2024Efficient Exploration for LLMscited by 44
  5. 2021EE-Net: Exploitation-Exploration Neural Networks in Contextual Banditscited by 43
  6. 2022Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexitycited by 31
  7. 2021From Predictions to Decisions: The Importance of Joint Predictive Distributionscited by 28
  8. 2021Deciding What to Learn: A Rate-Distortion Approachcited by 23
  9. 2022An Analysis of Ensemble Samplingcited by 23
  10. 2021Information Directed Sampling for Sparse Linear Banditscited by 20
  11. 2023Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Explorationcited by 20
  12. 2022Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Banditscited by 19
38 more
  1. 2022Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learningcited by 19
  2. 2022Ensembles for Uncertainty Estimation: Benefits of Prior Functions and Bootstrappingcited by 19
  3. 2021The Value of Information When Deciding What to Learncited by 15
  4. 2025Toward Efficient Exploration by Large Language Model Agentscited by 15
  5. 2021Deep Exploration for Recommendation Systemscited by 14
  6. 2024PageRank Bandits for Link Predictioncited by 14
  7. 2023Leveraging Demonstrations to Improve Online Learning: Quality Matterscited by 13
  8. 2023Exploration via linearly perturbed loss minimisationcited by 13
  9. 2023Pearl: A Production-ready Reinforcement Learning Agentcited by 9
  10. 2024Improving sample efficiency of high dimensional Bayesian optimization with MCMCcited by 9
  11. 2023Shattering the Agent-Environment Interface for Fine-Tuning Inclusive Language Modelscited by 8
  12. 2025When and why randomised exploration works (in linear bandits)cited by 8
  13. 2021Anti-Concentrated Confidence Bonuses for Scalable Explorationcited by 7
  14. 2022Deep Active Ensemble Sampling For Image Classificationcited by 7
  15. 2023Neural Exploitation and Exploration of Contextual Banditscited by 7
  16. 2023Ensemble sampling for linear bandits: small ensembles sufficecited by 7
  17. 2024Online Bandit Learning with Offline Preference Data for Improved RLHFcited by 6
  18. 2024Improved Regret of Linear Ensemble Samplingcited by 6
  19. 2022Conservative Dual Policy Optimization for Efficient Model-Based Reinforcement Learningcited by 5
  20. 2023Langevin Thompson Sampling with Logarithmic Communication: Bandits and Reinforcement Learningcited by 5
  21. 2023VITS : Variational Inference Thompson Sampling for contextual banditscited by 5
  22. 2025Contextual Thompson Sampling via Generation of Missing Datacited by 5
  23. 2025Bayesian Optimization with Inexact Acquisition: Is Random Grid Search Sufficient?cited by 4
  24. 2026Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Modelscited by 4
  25. 2021Learning to Be Cautiouscited by 3
  26. 2023Multiplier Bootstrap-based Explorationcited by 3
  27. 2024Tree Ensembles for Contextual Banditscited by 3
  28. 2025Best Policy Learning from Trajectory Preference Feedbackcited by 3
  29. 2022Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Frameworkcited by 2
  30. 2022Multi-armed bandits for resource efficient, online optimization of language model pre-training: the use case of dynamic maskingcited by 2
  31. 2023Pessimistic Off-Policy Multi-Objective Optimizationcited by 2
  32. 2025Distance-Aware Error for Spline Networks: A Bottom-Up Approach to Uncertaintycited by 2
  33. 2025Provable Anytime Ensemble Sampling Algorithms in Nonlinear Contextual Banditscited by 2
  34. 2026Optimism Stabilizes Thompson Sampling for Adaptive Inferencecited by 2
  35. 2020Distilled Thompson Sampling: Practical and Efficient Thompson Sampling via Imitation Learningcited by 1
  36. 2021CORe: Capitalizing On Rewards in Bandit Explorationcited by 1
  37. 2021Optimizing over an ensemble of neural networkscited by 1
  38. 2022Regenerative Particle Thompson Samplingcited by 1

50 most cited of 62 All 62 (JSON)