# Bandit Social Learning: Exploration under Myopic Behavior

arXiv: https://arxiv.org/abs/2302.07425 · HTML: https://mlsanity.com/paper/2302.07425/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 70 references that are in the map.
- First posted on arXiv 15 Feb 2023.

## Builds on (most cited first, 12 of 12)

- [Introduction to Multi-Armed Bandits](https://mlsanity.com/paper/1904.07272/) (2019)
- [A Tutorial on Thompson Sampling](https://mlsanity.com/paper/1707.02038/) (2017)
- [Mostly Exploration-Free Algorithms for Contextual Bandits](https://mlsanity.com/paper/1704.09011/) (2017)
- [Bayesian Incentive-Compatible Bandit Exploration](https://mlsanity.com/paper/1502.04147/) (2015)
- [The Unreasonable Effectiveness of Greedy Algorithms in Multi-Armed Bandit with Many Arms](https://mlsanity.com/paper/2002.10121/) (2020)
- [The Price of Incentivizing Exploration: A Characterization via Thompson Sampling and Sample Complexity](https://mlsanity.com/paper/2002.00558/) (2020)
- [Incentivizing Exploration with Selective Data Disclosure](https://mlsanity.com/paper/1811.06026/) (2018)
- [The Externalities of Exploration and How Data Diversity Helps Exploitation](https://mlsanity.com/paper/1806.00543/) (2018)
- [Greedy Algorithm almost Dominates in Smoothed Contextual Bandits](https://mlsanity.com/paper/2005.10624/) (2020)
- [On the Non-asymptotic and Sharp Lower Tail Bounds of Random Variables](https://mlsanity.com/paper/1810.09006/) (2018)
- [Be Greedy in Multi-Armed Bandits](https://mlsanity.com/paper/2101.01086/) (2021)
- [Incentivizing Exploration with Heterogeneous Value of Money](https://mlsanity.com/paper/1512.08427/) (2015)

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

- [Can large language models explore in-context?](https://mlsanity.com/paper/2403.15371/) (2024)
- [Incentivized Learning in Principal-Agent Bandit Games](https://mlsanity.com/paper/2403.03811/) (2024)
- [Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure](https://mlsanity.com/paper/2503.04010/) (2025)
- [Incentivized Collaboration in Active Learning](https://mlsanity.com/paper/2311.00260/) (2023)
- [Dueling Over Dessert, Mastering the Art of Repeated Cake Cutting](https://mlsanity.com/paper/2402.08547/) (2024)
- [Envy-Free Allocation of Indivisible Goods via Noisy Queries](https://mlsanity.com/paper/2602.06361/) (2026)

## Abstract (arXiv)

We study social learning dynamics motivated by reviews on online platforms. The agents collectively follow a simple multi-armed bandit protocol, but each agent acts myopically, without regards to exploration. We allow the greedy (exploitation-only) algorithm, as well as a wide range of behavioral biases. Specifically, we allow myopic behaviors that are consistent with (parameterized) confidence intervals for the arms' expected rewards. We derive stark learning failures for any such behavior, and provide matching positive results. The learning-failure results extend to Bayesian agents and Bayesian bandit environments. In particular, we obtain general, quantitatively strong results on failure of the greedy bandit algorithm, both for ``frequentist" and ``Bayesian" versions. Failure results known previously are quantitatively weak, and either trivial or very specialized. Thus, we provide a theoretical foundation for designing non-trivial bandit algorithms, ie algorithms that intentionally explore, which has been missing from the literature. Our general behavioral model can be interpreted as agents' optimism or pessimism. The matching positive results entail a maximal allowed amount of optimism. Moreover, we find that no amount of pessimism helps against the learning failures, whereas even a small-but-constant fraction of extreme optimists avoids the failures and leads to near-optimal regret rates.