Markov Persuasion Processes: Learning to Persuade from Scratch
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917605533548544 |
|---|---|
| author | Bacchiocchi, Francesco Stradi, Francesco Emanuele Castiglioni, Matteo Marchesi, Alberto Gatti, Nicola |
| author_facet | Bacchiocchi, Francesco Stradi, Francesco Emanuele Castiglioni, Matteo Marchesi, Alberto Gatti, Nicola |
| contents | In Bayesian persuasion, an informed sender strategically discloses information to a receiver so as to persuade them to undertake desirable actions. Recently, a growing attention has been devoted to settings in which sender and receivers interact sequentially. Recently, Markov persuasion processes (MPPs) have been introduced to capture sequential scenarios where a sender faces a stream of myopic receivers in a Markovian environment. The MPPs studied so far in the literature suffer from issues that prevent them from being fully operational in practice, e.g., they assume that the sender knows receivers' rewards. We fix such issues by addressing MPPs where the sender has no knowledge about the environment. We design a learning algorithm for the sender, working with partial feedback. We prove that its regret with respect to an optimal information-disclosure policy grows sublinearly in the number of episodes, as it is the case for the loss in persuasiveness cumulated while learning. Moreover, we provide a lower bound for our setting matching the guarantees of our algorithm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_03077 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Markov Persuasion Processes: Learning to Persuade from Scratch Bacchiocchi, Francesco Stradi, Francesco Emanuele Castiglioni, Matteo Marchesi, Alberto Gatti, Nicola Computer Science and Game Theory Machine Learning In Bayesian persuasion, an informed sender strategically discloses information to a receiver so as to persuade them to undertake desirable actions. Recently, a growing attention has been devoted to settings in which sender and receivers interact sequentially. Recently, Markov persuasion processes (MPPs) have been introduced to capture sequential scenarios where a sender faces a stream of myopic receivers in a Markovian environment. The MPPs studied so far in the literature suffer from issues that prevent them from being fully operational in practice, e.g., they assume that the sender knows receivers' rewards. We fix such issues by addressing MPPs where the sender has no knowledge about the environment. We design a learning algorithm for the sender, working with partial feedback. We prove that its regret with respect to an optimal information-disclosure policy grows sublinearly in the number of episodes, as it is the case for the loss in persuasiveness cumulated while learning. Moreover, we provide a lower bound for our setting matching the guarantees of our algorithm. |
| title | Markov Persuasion Processes: Learning to Persuade from Scratch |
| topic | Computer Science and Game Theory Machine Learning |
| url | https://arxiv.org/abs/2402.03077 |