Optimally Installing Strict Equilibria
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916644479041536 |
|---|---|
| author | McMahan, Jeremy Wu, Young Chen, Yudong Zhu, Xiaojin Xie, Qiaomin |
| author_facet | McMahan, Jeremy Wu, Young Chen, Yudong Zhu, Xiaojin Xie, Qiaomin |
| contents | In this work, we develop a reward design framework for installing a desired behavior as a strict equilibrium across standard solution concepts: dominant strategy equilibrium, Nash equilibrium, correlated equilibrium, and coarse correlated equilibrium. We also extend our framework to capture the Markov-perfect equivalents of each solution concept. Central to our framework is a comprehensive mathematical characterization of strictly installable, based on the desired solution concept and the behavior's structure. These characterizations lead to efficient iterative algorithms, which we generalize to handle optimization objectives through linear programming. Finally, we explore how our results generalize to bounded rational agents. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_03676 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Optimally Installing Strict Equilibria McMahan, Jeremy Wu, Young Chen, Yudong Zhu, Xiaojin Xie, Qiaomin Computer Science and Game Theory Machine Learning In this work, we develop a reward design framework for installing a desired behavior as a strict equilibrium across standard solution concepts: dominant strategy equilibrium, Nash equilibrium, correlated equilibrium, and coarse correlated equilibrium. We also extend our framework to capture the Markov-perfect equivalents of each solution concept. Central to our framework is a comprehensive mathematical characterization of strictly installable, based on the desired solution concept and the behavior's structure. These characterizations lead to efficient iterative algorithms, which we generalize to handle optimization objectives through linear programming. Finally, we explore how our results generalize to bounded rational agents. |
| title | Optimally Installing Strict Equilibria |
| topic | Computer Science and Game Theory Machine Learning |
| url | https://arxiv.org/abs/2503.03676 |