mlsanityData to 14 Oct 2026

Incentivizing Exploration with Selective Data Disclosure

arXiv 1811.06026 ↗First posted 14 Nov 2018cs.GT cs.DS cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

We propose and design recommendation systems that incentivize efficient exploration. Agents arrive sequentially, choose actions and receive rewards, drawn from fixed but unknown action-specific distributions. The recommendation system presents each agent with actions and rewards from a subsequence of past agents, chosen ex ante. Thus, the agents engage in sequential social learning, moderated by these subsequences. We asymptotically attain optimal regret rate for exploration, using a flexible frequentist behavioral model and mitigating rationality and commitment assumptions inherent in prior work. We suggest three components of effective recommendation systems: independent focus groups, group aggregators, and interlaced information structures.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). First posted on arXiv 14 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 3; 2023: 6; 2024: 5; 2025: 3; 2026: 3.

24 papers.

Sort:

By area:

  1. 2021Fair Exploration via Axiomatic Bargainingcited by 22
  2. 2022Fundamentals of Task-Agnostic Data Valuationcited by 19
  3. 2021Exploration and Incentives in Reinforcement Learningcited by 11
  4. 2022Incentivizing Combinatorial Bandit Explorationcited by 9
  5. 2023Bandit Social Learning: Exploration under Myopic Behaviorcited by 6
  6. 2021Incentivizing Exploration in Linear Bandits under Information Gapcited by 5
  7. 2022Incentive-Aware Recommender Systems in Two-Sided Marketscited by 5
  8. 2023Algorithmic Censoring in Dynamic Learning Systemscited by 5
  9. 2023Incentivizing Exploration with Linear Contexts and Combinatorial Actionscited by 5
  10. 2023When Are Two Lists Better than One?: Benefits and Harms in Joint Decision-makingcited by 4
  11. 2024How to Strategize Human Content Creation in the Era of GenAI?cited by 4
  12. 2021(Almost) Free Incentivized Exploration from Decentralized Learning Agentscited by 3
12 more
  1. 2026Multi-Round Human-AI Collaboration with User-Specified Requirementscited by 3
  2. 2024Incentivized Exploration via Filtered Posterior Samplingcited by 2
  3. 2024Learning from Imperfect Human Feedback: a Tale from Corruption-Robust Duelingcited by 2
  4. 2024Misalignment, Learning, and Ranking: Harnessing Users Limited Attentioncited by 1
  5. 2024Exploration and Persuasioncited by 1
  6. 2025Truthful mechanisms for linear bandit games with private contextscited by 1
  7. 2023Incentivized Collaboration in Active Learningcited by 0
  8. 2023Incentive-Aware Synthetic Control: Accurate Counterfactual Estimation via Incentivized Explorationcited by 0
  9. 2025Learning with Limited Shared Information in Multi-agent Multi-armed Banditcited by 0
  10. 2025Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contextscited by 0
  11. 2026Prior-Agnostic Incentive-Compatible Explorationcited by 0
  12. 2026On Incentivized Exploration beyond Bayesianism and Full-Informationcited by 0