3 papers
cs.GT2026
Leveraging Machine-Learned Advice in Strategic Interactions with No-Regret Learners
Tinashe Handina, Tongxin Li, Kishan Panaganti +2
We study how an agent in a two-player repeated game can effectively utilize potentially imperfect advice when interacting with a no-regret learner. We characterize the advice lands…
cs.GT2024
Understanding Model Selection For Learning In Strategic Environments
Tinashe Handina, Eric Mazumdar
The deployment of ever-larger machine learning models reflects a growing consensus that the more expressive the model class one optimizes over$\unicode{x2013}$and the more data one…
cs.LG2024
Safe Exploitative Play with Untrusted Type Beliefs
Tongxin Li, Tinashe Handina, Shaolei Ren +1
The combination of the Bayesian game and learning has a rich history, with the idea of controlling a single agent in a system composed of multiple agents with unknown behaviors giv…