Bandit Social Learning: Exploration Under Myopic Behavior

Abstract

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 intentional

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybanihashem2023bandit

Related papers

• Bandit Social Learning With Exploration Episodes (2026)0.00
• Principal-agent Bandit Games With Self-interested And Exploratory Learning Agents (2024)0.00
• Near-optimal Collaborative Learning In Bandits (2022)0.00
• Bayesian Bandits: Balancing The Exploration-exploitation Tradeoff Via Double Sampling (2017)0.00
• Exploiting Expertise Of Non-expert And Diverse Agents In Social Bandit Learning: A Free Energy Approach (2026)0.00
• A New Bandit Setting Balancing Information From State Evolution And Corrupted Context (2020)0.00
• Off-policy Evaluation And Learning From Logged Bandit Feedback: Error Reduction Via Surrogate Policy (2018)0.00
• Online Learning For Cooperative Multi-player Multi-armed Bandits (2021)5.24