Timezone: »

A New Formalism, Method and Open Issues for Zero-Shot Coordination
Johannes Treutlein · Michael Dennis · Caspar Oesterheld · Jakob Foerster

Tue Jul 20 09:00 AM -- 11:00 AM (PDT) @ None #None

In many coordination problems, independently reasoning humans are able to discover mutually compatible policies. In contrast, independently trained self-play policies are often mutually incompatible. Zero-shot coordination (ZSC) has recently been proposed as a new frontier in multi-agent reinforcement learning to address this fundamental issue. Prior work approaches the ZSC problem by assuming players can agree on a shared learning algorithm but not on labels for actions and observations, and proposes other-play as an optimal solution. However, until now, this “label-free” problem has only been informally defined. We formalize this setting as the label-free coordination (LFC) problem by defining the label-free coordination game. We show that other-play is not an optimal solution to the LFC problem as it fails to consistently break ties between incompatible maximizers of the other-play objective. We introduce an extension of the algorithm, other-play with tie-breaking, and prove that it is optimal in the LFC problem and an equilibrium in the LFC game. Since arbitrary tie-breaking is precisely what the ZSC setting aims to prevent, we conclude that the LFC problem does not reflect the aims of ZSC. To address this, we introduce an alternative informal operationalization of ZSC as a starting point for future work.

Author Information

Johannes Treutlein (University of Toronto, Vector Institute)
Michael Dennis (UC Berkeley)
Caspar Oesterheld (Duke)
Jakob Foerster (Facebook AI Research)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors