Timezone: »

Contextual Games: Multi-Agent Learning with Side Information
Pier Giuseppe Sessa · Ilija Bogunovic · Andreas Krause · Maryam Kamgarpour

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1466

We formulate the novel class of contextual games, a type of repeated games driven by contextual information at each round. By means of kernel-based regularity assumptions, we model the correlation between different contexts and game outcomes and propose a novel online (meta) algorithm that exploits such correlations to minimize the contextual regret of individual players. We define game-theoretic notions of contextual Coarse Correlated Equilibria (c-CCE) and optimal contextual welfare for this new class of games and show that c-CCEs and optimal welfare can be approached whenever players' contextual regrets vanish. Finally, we empirically validate our results in a traffic routing experiment, where our algorithm leads to better performance and higher welfare compared to baselines that do not exploit the available contextual information or the correlations present in the game.

Author Information

Pier Giuseppe Sessa (ETH Zürich)
Ilija Bogunovic (ETH Zurich)
Andreas Krause (ETH Zurich)
Maryam Kamgarpour (ETH Zürich)

More from the Same Authors