Discovering how agents learn using few data

[PDF] arxiv.org

Steering game dynamics towards desired outcomes

I Canyakmaz, I Sakos, W Lin, A Varvitsiotis… - arXiv preprint arXiv …, 2024 - arxiv.org
The dynamic behavior of agents in games, which captures how their strategies evolve over
time based on past interactions, can lead to a spectrum of undesirable behaviors, ranging …
被引用次数：2 相关文章 所有 2 个版本
[PDF] openreview.net

Learning and Steering Game Dynamics Towards Desirable Outcomes

I Canyakmaz, I Sakos, W Lin, A Varvitsiotis, G Piliouras - openreview.net
Game dynamics, which describe how agents' strategies evolve over time based on past
interactions, can exhibit a variety of undesirable behaviours, including convergence to …
相关文章