# Meta-Learning for Repeated Bayesian Persuasion

arXiv: https://arxiv.org/abs/2603.20408 · HTML: https://mlsanity.com/paper/2603.20408/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 20 Mar 2026.

## Builds on (most cited first, 15 of 15)

- [Adaptive Gradient-Based Meta-Learning Methods](https://mlsanity.com/paper/1906.02717/) (2019)
- [Online Convex Optimization in Adversarial Markov Decision Processes](https://mlsanity.com/paper/1905.07773/) (2019)
- [Meta-Thompson Sampling](https://mlsanity.com/paper/2102.06129/) (2021)
- [Bayesian Exploration: Incentivizing Exploration in Bayesian Games](https://mlsanity.com/paper/1602.07570/) (2016)
- [No Regrets for Learning the Prior in Bandits](https://mlsanity.com/paper/2107.06196/) (2021)
- [Algorithmic Bayesian Persuasion](https://mlsanity.com/paper/1503.05988/) (2015)
- [Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning](https://mlsanity.com/paper/2202.10678/) (2022)
- [Optimal Rates and Efficient Algorithms for Online Bayesian Persuasion](https://mlsanity.com/paper/2303.01296/) (2023)
- [Multi-Receiver Online Bayesian Persuasion](https://mlsanity.com/paper/2106.06480/) (2021)
- [Meta-Learning in Games](https://mlsanity.com/paper/2209.14110/) (2022)
- [Markov Persuasion Processes: Learning to Persuade from Scratch](https://mlsanity.com/paper/2402.03077/) (2024)
- [Meta-Learning Adversarial Bandits](https://mlsanity.com/paper/2205.14128/) (2022)
- [Information-Theoretic Approach to Strategic Communication as a Hierarchical Game](https://mlsanity.com/paper/1510.00764/) (2015)
- [Reputation-based Persuasion Platforms](https://mlsanity.com/paper/2305.16694/) (2023)
- [A Soft Inducement Framework for Incentive-Aided Steering of No-Regret Players](https://mlsanity.com/paper/2508.21672/) (2025)

## Abstract (arXiv)

Classical Bayesian persuasion studies how a sender influences receivers through carefully designed signaling policies within a single strategic interaction. In many real-world environments, such interactions are repeated across multiple games, creating opportunities to exploit structural similarity across tasks. In this work, we introduce Meta-Persuasion algorithms, establishing the first line of theoretical results for both full-feedback and bandit-feedback settings in the Online Bayesian Persuasion (OBP) and Markov Persuasion Process (MPP) frameworks. We show that our proposed meta-persuasion algorithms achieve provably sharper regret rates under natural notions of task similarity, improving upon the best-known convergence rates for both OBP and MPP. At the same time, they recover the standard single-game guarantees when the sequence of games is picked arbitrarily. Finally, we complement our theoretical analysis with numerical experiments that highlight our regret improvements and the benefits of meta-learning in repeated persuasion environments.