- Conference Paper
We consider a repeated sequential game between a learner, who plays first, and an opponent who responds to the chosen action. We seek to design strategies for the learner to successfully interact with the opponent. While most previous approaches consider known opponent models, we focus on the setting in which the opponent's model is unknown. To this end, we use kernel-based regularity assumptions to capture and exploit the structure in the opponent's response. We propose a novel algorithm for the learner when playing against an adversarial sequence of opponents. The algorithm combines ideas from bilevel optimization and online learning to effectively balance between exploration (learning about the opponent's model) and exploitation (selecting highly rewarding actions for the learner). Our results include algorithm's regret guarantees that depend on the regularity of the opponent's response and scale sublinearly with the number of game rounds. Moreover, we specialize our approach to repeated Stackelberg games, and empirically demonstrate its effectiveness in a traffic routing and wildlife conservation task. Show more
Book titleAdvances in Neural Information Processing Systems 33
Pages / Article No.
Organisational unit03908 - Krause, Andreas / Krause, Andreas
09578 - Kamgarpour, Maryam / Kamgarpour, Maryam
815943 - Reliable Data-Driven Decision Making in Cyber-Physical Systems (EC)
19-2 FEL-47 - Robust Sample-Efficient Learning when Data ist Costly (ETHZ)
NotesConference lecture held on December 9, 2020 . Due to the Coronavirus (COVID-19) the conference was conducted virtually.
MoreShow all metadata